Search

The inventory management of medical items in humanitarian operations is a challenging task due to the intermittent nature of their demand and long replenishment lead-times. An effective response to humanitarian emergencies is often associated with excess inventories, which leads to high costs. Henceforth, using accurate demand forecasts to control the inventories of these medical items is shown to be a significant lever to reduce inventory costs while keeping high service levels. This paper investigates the effectiveness of parametric and non-parametric demand forecasting methods that are commonly considered to deal with items characterised with intermittent demand patterns. Moreover, we propose a new hybrid deep learning method that combines the long short-term memory neural network and the support vector regression. Such combination enables to deal with complex and non-linear data. We conduct an empirical investigation by means of data related to 523 medical items managed in two warehouses of a major humanitarian organisation. The forecast accuracy and the inventory efficiency of the methods are analysed. The empirical results show the high performance of the deep learning methods. These insights are valuable not only in the context of medical items in humanitarian operations, but also for any items with intermittent demand patterns. [ABSTRACT FROM AUTHOR]

In the rapidly evolving landscape, digitising the operations and facilities in a supply chain network is essential to make the system autonomous and develop strategies for enhancing resilience, transparency, and efficiency. The COVID-19 pandemic highlights the necessity of sustainable solutions for the hybrid mode of operations. To overcome several challenges, including price optimisation, demand forecasting under uncertainty, supply-demand gap reduction, take into account vulnerability, competitive business environment and risk, the supply chain needs to be streamlined with technology-driven infrastructures incorporating physical and information flow into overall supply chain processes. The digitisation aspect encompasses adopting cutting-edge technologies such as enterprise resource planning (ERP) for supply chain visibility, e-hailing platforms, real-time data analytics, the Internet of Things (IoT) and Internet of Behaviour (IoB), blockchain-driven technology, as well as additive manufacturing, enabling seamless connectivity and communication among diverse stakeholders. This revolution enables strategic integration of various entities and state of the art data-driven decision-making, providing real-time insights into logistics movements, demand forecasting, production planning and inventory levels. Supply chain digitisation and management emphasises collaboration with supply chain partners to identify important factors, optimise costs and enhance overall supply chain resilience. Digitisation and management are technological evolutions and strategic shifts integrating analytical tools, allowing businesses to formulate models to improve performance. The implementation of blockchain-driven technology solidifies trust and safety transactions by creating an immutable and transparent log, mitigating threats and enhancing traceability. Digitisation and management exemplify a transformative journey towards a more connected, data-driven, and agile global supply chain ecosystem. [ABSTRACT FROM AUTHOR]

Forecasting for intermittent demand is considered a difficult task and becomes even more challenging in the presence of obsolescence. Traditionally the problem has been dealt with modifications in the conventional parametric methods such as Croston. However, these methods are generally applied at the observed frequency, ignoring any additional information, such as trend that becomes prominent at higher levels of aggregation. We evaluate established Temporal Aggregation (TA) methods: ADIDA, Forecast Combination, and Temporal Hierarchies in the said context. We further employ restricted least-squares estimation and propose two new combination approaches tailored to decreasing demand scenarios. Finally, we test our propositions on both simulated and real datasets. Our empirical findings support the use of variable forecast combination weights to improve TA's performance in intermittent demand items with a risk of obsolescence. [ABSTRACT FROM AUTHOR]

Forecasts of demands or prices become increasingly unreliable as the future becomes more distant. It is, therefore, beneficial to show that optimal decisions during an initial time interval are either partially or wholly independent of the forecasted data from some future time onwards. Using a commodity trading model as an example, we obtain conditions that allow us to make optimal buying and selling decisions for a commodity in some initial time interval without knowing its price forecast beyond some future time. Such an initial time interval is called a decision horizon and the time up to which the forecasted data is required to make the optimal decisions during the decision horizon is called a forecast horizon. We use the maximum principle to solve the example and show that the decision and forecast horizons in the problem arise from lower and upper bounds imposed on the on-hand inventory of the commodity. [ABSTRACT FROM AUTHOR]

Intermittent demand forecasting is a ubiquitous and challenging problem in production systems and supply chain management. In recent years, there has been a growing focus on developing forecasting approaches for intermittent demand from academic and practical perspectives. However, limited attention has been given to forecast combination methods, which have achieved competitive performance in forecasting fast-moving time series. The current study examines the empirical outcomes of some existing forecast combination methods and proposes a generalised feature-based framework for intermittent demand forecasting. The proposed framework has been shown to improve the accuracy of point and quantile forecasts based on two real data sets. Further, some analysis of features, forecasting pools and computational efficiency is also provided. The findings indicate the intelligibility and flexibility of the proposed approach in intermittent demand forecasting and offer insights regarding inventory decisions. [ABSTRACT FROM AUTHOR]

With the explosion of e-commerce, optimising parcel transportation has become increasingly important. We study the long-haul stage of parcel transportation which takes place between sorting centres and delivery depots and is performed on a two-level hierarchical network. In our case study, we describe the application framework of this industrial problem faced by a French postal company: There are two vehicle types that must be balanced over the network on a daily basis, and there are two possible sorting points for each parcel, which allows a better consolidation of parcels. These industrial constraints are formalised in the Long-Haul Parcel Transportation Problem (LHPTP). We present a Mixed Integer Linear Program (MILP) and a hierarchical algorithm with aggregation of demands which uses the MILP as a subroutine. We perform numerical experiments on large-size datasets provided by a postal company, which consist of approximately 2500 demands on a network of 225 sites. These tests enable the tuning of certain parameters resulting in a tailored heuristic for the LHPTP. Our algorithm can serve as a decision aid tool for transportation managers to build daily transportation plans, modeled on solutions produced given daily demand forecasts and can also be used to improve the network design. [ABSTRACT FROM AUTHOR]

Human-centricity is the core value behind the evolution of manufacturing towards Industry 5.0. Nevertheless, there is a lack of architecture that considers safety, trustworthiness, and human-centricity at its core. Therefore, we propose an architecture that integrates Artificial Intelligence (Active Learning, Forecasting, Explainable Artificial Intelligence), simulated reality, decision-making, and users' feedback, focussing on synergies between humans and machines. Furthermore, we align the proposed architecture with the Big Data Value Association Reference Architecture Model. Finally, we validate it on three use cases from real-world case studies. [ABSTRACT FROM AUTHOR]

Efficient resource management methods are essential for spare parts used in the maintenance and repair of equipment. Forecasting plays a critical role in planning, especially under demand uncertainty. Existing works regarding spare parts with intermittent demand focus on the mere forecasting model while integrating the planning and forecasting models are not sufficiently investigated. We examine the interaction between two models to optimise planning and forecasting decisions and prevent sub-optimality. This paper presents two mathematical models, including a planning model that determines stock level, spare part order assignment to suppliers, equipment repair assignment, and the number of intervals over the planning horizon. The second model is the forecasting model by Support Vector Machine (SVM). Considering uncertainty, demand estimation is performed by piecewise linearisation considering the optimal number of intervals in the planning model used in forecasting. An interactive procedure is developed to optimise models. We use an empirical investigation from an oil company providing the spare part supply chain data. The analyses show that demand estimation by piecewise method and integrating the decisions optimises the cost, improves the forecasting accuracy, and planning performance. Moreover, we offer several insights to practitioners that shed light on spare part planning and forecasting decisions. [ABSTRACT FROM AUTHOR]

This study investigates the role of human intervention in artificial intelligence/machine learning (AIML)-driven predictions. By doing so, we distinguish between three different types of human-AIML collaboration: automation, adjustable automation, and augmentation. We theorize that prediction uncertainty and time horizon represent two critical determinants of forecast accuracy. Based on a field experiment involving AIML-driven demand forecasts approximately 1,888 stock-keeping units in the retail industry, we rely on a multivalued treatment effect methodology to measure the effects of human-AIML collaboration on forecast accuracy. Our findings show that human intervention complements AIML-driven forecasts most effectively (augmentation) in predictions with long time horizons and low uncertainty. However human intervention is least likely to contribute to the effectiveness of AIML predictions (automation) in environments with short time horizons and high uncertainty. We discuss implications for extant theory and propose a framework outlining the conditions in which human intervention is most likely to add predictive value to human-AIML collaborations. [ABSTRACT FROM AUTHOR]

We explore the impact of judgement bias on demand forecast accuracy and profit to identify the driving force of decision-makers to be biased. We study the accuracy-maximising forecasts and the profit-maximising forecasts, which results in the least error of demand forecasts and minimum deviation from the optimal order decision, respectively. Under the assumption that period-to-period demand is independent over time, we find that both types of forecasts are biased. It implies that a newsvendor has the motivation to be biased to obtain either a more accurate demand forecast or a higher profit. Moreover, the decision error under the accuracy-maximising forecasts can be lower than that under unbiased demand forecasts and be bounded by twice of the error under profit-maximising forecasts. It suggests that the biased accuracy-maximising forecasts can perform satisfactorily in both forecasts and decisions. We further relax the assumption of independent demand by considering correlated and trended demand processes, and show the robustness of the positive impact of judgement bias. We then propose a method to solve pure data-driven newsvendor problem and examine its performance with empirical evidence. Our paper contributes to the literature on behavioural operations management by investigating the rationality of judgement bias and its implications. [ABSTRACT FROM AUTHOR]

Social manufacturing is conceptualised as a new type of networked manufacturing paradigm that supports the organisation of socialised manufacturing resources (SMRs) to satisfy the growth of personalised demands on crowd intelligence in a timely manner when co-creating open architecture products. The high participation of each stakeholder in this type of product production places a higher requirement on sufficient collaboration among social, cyber and physical spaces. However, under a decentralised social manufacturing network, the management of SMRs has encountered some real-life challenges in terms of their distributed and heterogeneous features. Hence, this paper proposes a blockchain-enabled digital twin collaboration platform (BcDTCP) as an integrated solution to address these challenges. A hybrid domain-driven design method is presented to design and implement business-knowledge driven systems. To address the heterogeneity of SMRs, a ubiquitous object structure is designed to flexibly adjust the functionality of the digital twin. Blockchain is introduced to construct a peer-to-peer network to organise the SMRs in a decentralised manner. Additionally, a timed coloured Petri net-based workflow is adopted to formulise the collaboration logic into a smart contract executed on the blockchain. Finally, a demonstrative case study is conducted to verify and evaluate the proposed BcDTCP under a 3D printing scenario. [ABSTRACT FROM AUTHOR]

The development of digital technology, such as data mining and analysis techniques, has enabled e-commerce platforms to use the data generated in their ecosystems and forecast the online demand more accurately. By sharing the forecast information, platforms help their partners reduce the demand uncertainty. To examine the effects of the shared information, this study considers a two-echelon supply chain consisting of one original equipment manufacturer (OEM), one brand store, and one platform, and investigates the relations between the forecast information and firms' channel strategies. Our analysis reveals some interesting implications. First, the platform's forecast information encourages the OEM to develop online business unless the brand store adopts the dual-channel strategy and the platform sets the revenue commission as zero, while it always increases the brand store's willingness to adopt the dual-channel strategy. Moreover, the OEM's online business hinders the platform to share the information if consumers' acceptance for the brand in online channel is low. Interestingly, the brand store's dual-channel strategy hinders the platform to share the information if consumers' acceptance for the brand in online channel is high. Further, we find that when the brand store adopts the dual-channel strategy, the OEM's online business always decreases the benefit of the forecast information for the brand store. However, when the OEM develops online business, the brand store's dual-channel strategy sometimes increases the benefit of the forecast information for the OEM. In addition, we also conduct some numerical experiments to examine the impacts of the platform commission rate on these firms' benefits from the information and find that the higher commission rate can increase the OEM's benefit under certain conditions. Our study aims to provide managerial insights for the OEM, brand store, and platform to capture the value of forecast information. [ABSTRACT FROM AUTHOR]

The economy of a country is directly proportional to the power sector of that country. An unmanaged power sector causes instability in the country. Pakistan is also facing this phenomenon due to uncontrolled power outage and circular debt. Pakistan's power sector is analyzed as a case study to find out the root cause for the unmanaged power sector and for proposing the most effective data-driven solution. After a literature review and discussion with domain experts, it was found that inaccurate power demand forecast is one of the main reasons for power crisis in Pakistan. Under-forecasting caused load shedding, and over-forecasting increased circular debt due to idle capacity payments. Previously, traditional statistical methods were used for power demand forecasting. The multiple linear regression model that is being used since 2018 (IGCEP) uses features such as previous year load and demographic and economic variables for long-term peak power demand forecasting till 2030. The problem is that the independent variables used in existing models are manipulated and cause a gap between actual and forecasted power demand. Moreover, even yearly peak power demand is not absolutely linear in nature; hence, it is necessary to apply AI-based techniques that can handle nonlinearity effectively. Not using system-generated data, not using the most appropriate features, not using an appropriate forecasting time horizon, and not using the appropriate forecasting model are main reasons for inaccurate peak power demand forecasting. The issue can be resolved by forecasting monthly peak power demand for the next 5 years by using the National Power Control Center's (NPCC) system-generated data. Accurate monthly peak load forecasting leads to accurate yearly peak power demand. The monthly peak load forecasting strategy not only helps in managing operational issues of the power sector such as fuel scheduling and power plant maintenance scheduling but also guides decision-makers toward power and transmission expansion or contraction in the long term. More accurate monthly peak power demand forecasting can be achieved by applying nonlinear AI models in a comprehensive dataset comprising new engineered features, climate features, and the number of consumers. All these features are mostly system-generated and cannot be manipulated. As a result, the accuracy is improved and the results are more reliable than those of the existing models. The new features can be engineered from recent monthly peak load data generated by the system operator (NPCC). Climate features are collected from the Meteorological Department of Pakistan through sensors or database connectivity. The number of electricity consumers can be extracted from NEPRA's state-of-industry report. All three datasets are combined on a common key (month-year) to a comprehensive dataset, which is passed through different AI models. In the experimental setup, it is found that support vector regression (SVR) produces the most accurate results, with an R-square of 99%, RMSE of 28, and MAPE of 0.1355, which are the best results compared to the literature reviewed. [ABSTRACT FROM AUTHOR]

This paper provides an in-depth discussion on the comprehensive requirements analysis, design implementation, algorithm optimization, and experimental evaluation of an electric power marketing information system, aiming to build a modern information system that is efficient, secure, and user-friendly. In the requirements analysis phase, the importance of business process optimization, data management analysis, security compliance, system integration and scalability is emphasized, while the diversified needs of end customers are considered. For the design and implementation part, the system architecture is based on microservices and cloud-native technologies to ensure high performance and security; and modularized development is achieved through Spring Boot, Vue.js and other technology stacks. For algorithm optimization, LSTM is used for power demand prediction and anomaly detection by combining integrated learning and self-encoder, which improves the prediction accuracy and anomaly identification capability. Experimental evaluation shows that the system demonstrates good performance, security and scalability in cloud computing environment, and the cost-effectiveness is significantly better than traditional deployment. [ABSTRACT FROM AUTHOR]

IoT applications have greatly improved the convenience of our lives, generating large amounts of IoT data. How to efficiently use these data to feed IoT applications has become a significant research problem, and many studies have used machine learning methods for advanced IoT data analytics. However, the prediction models of these studies generally suffer from the problem of easy overfitting, and insufficient work done on the analysis and selection of features. In terms of prediction models, this paper proposes a second-order hybrid fusion weight–median (W–M) algorithm, which first ensures the sensitivity of the data by weighted average fusion and then reduces the impact of extreme values on the data by median fusion. In terms of feature analysis and selection, this study constructed feature crosses by studying time and weather factors and proposes a second-order feature selection, recursive feature elimination-cross validation-Pearson correlation coefficient (RFECV-PCC) algorithm, which combines the RFECV method and Pearson correlation coefficient for feature selections. Experiments were conducted to evaluate the prediction results using root mean square logarithmic error (RMSLE) and comparison of the simulation results of the dataset, which the real-time data measurement showed that the W–M algorithm has the strongest RMSLE generalization ability, further improving the prediction accuracy after feature selection by the RFECV-PCC algorithm. [ABSTRACT FROM AUTHOR]

Accurate forecasting of duty-free shopping demand plays a pivotal role in strategic and operational decision-making processes. Despite the extensive literature on sustainability, operations management, and consumer behavior in the context of duty-free shopping, there is a noticeable absence of an integrated end-to-end solution for precise demand forecasting. Furthermore, existing forecasting models often encounter limitations in effectively leveraging multi-source data as reliable indicators for duty-free shopping demand. To address these gaps, our study introduces a pioneering deep-learning architecture known as the Attention-Aided Interaction-Driven Long Short-Term Memory-Convolutional Neural Network Model (AI-LCM). Designed to capture intricate cross-correlations within multi-source data, encompassing search queries, COVID-19 impact, economic factors, and historical data; this model represents a significant methodological advancement. Rigorous evaluation against state-of-the-art benchmarks conducted on robust real-world datasets confirms the superior forecasting performance exhibited by our AI-LCM model. We elucidate the manifold implications for various stakeholders while illustrating the extensive applicability of our model and its potential to inform data-driven decision-making strategies. [ABSTRACT FROM AUTHOR]

Intermittent demand forecasting is an important yet challenging task in many organizations. While prior research has been focused on traditional methods such as Croston's method and its variants, limited research has been conducted using advanced machine learning or deep learning methods. In this study, we introduce Transformer, a recently developed deep learning approach, to forecast intermittent demand. Its effectiveness is empirically tested with a dataset of 925 intermittent demand items from an airline spare parts provider and compared with that of two traditional methods such as Croston's and the Syntetos–Boylan approximation as well as several popular neural network architectures including feedforward neural networks, recurrent neural networks, and long short-term memory. Our results based on six different forecasting performance measures show that Transformer performs very well against other methods in a variety of settings. We also examine how data sparsity impacts model performance and find that different models perform similarly when sparsity is low. Although the performance of all models generally gets worse as the sparsity level increases, the advantage of Transformer over other models increases with sparsity. [ABSTRACT FROM AUTHOR]

Rating prediction is a crucial element of business analytics as it enables decision-makers to assess service performance based on expressive customer feedback. Enhancing rating score predictions and demand forecasting through incorporating performance features from verbatim text fields, particularly in service quality measurement and customer satisfaction modelling is a key objective in various areas of analytics. A range of methods has been identified in the literature for improving the predictability of customer feedback, including simple bag-of-words-based approaches and advanced supervised machine learning models, which are designed to work with response variables such as Likert-based rating scores. This paper presents a dynamic model that incorporates values from topic membership, an outcome variable from Latent Dirichlet Allocation, with sentiment analysis in an Extreme Gradient Boosting (XGBoost) model used for rating prediction. The results show that, by incorporating features from simple unsupervised machine learning approaches (LDA-based), an 86% prediction accuracy (AUC based) can be achieved on objective rating values. At the same time, a combination of polarity and single-topic membership can yield an even higher accuracy when compared with sentiment text detection tasks both at the document and sentence levels. This study carries significant practical implications since sentiment analysis tasks often require dictionary coverage and domain-specific adjustments depending on the task at hand. To further investigate this result, we used Shapley Additive Values to determine the additive predictability of topic membership values in combination with sentiment-based methods using a dataset of customer reviews from food delivery services. [ABSTRACT FROM AUTHOR]

In recent years, machine learning models based on big data have been introduced into marketing in order to transform customer data into meaningful insights and to make strategic decisions by making more accurate predictions. Although there is a large amount of literature on demand forecasting, there is a lack of research about how marketing strategies such as advertising and other promotional activities affect demand. Therefore, an accurate demand-forecasting model can make significant academic and practical contributions for business sustainability. The purpose of this article is to evaluate machine learning methods to provide accuracy in forecasting demand based on advertising expenses. The study focuses on a prediction mechanism based on several Machine Learning techniques—Support Vector Regression (SVR), Random Forest Regression (RFR) and Decision Tree Regressor (DTR) and deep learning techniques—Artificial Neural Network (ANN), Long Short Term Memory (LSTM),—to deal with demand forecasting based on advertising expenses. Deep learning is a powerful technique that can solve marketing problems based on both classification and regression algorithms. Accordingly, a television manufacturer's real market dataset consisting of advertising expenditures, sales and demand forecasting via chosen machine learning methods was analyzed and compared in terms of the accuracy of demand forecasting. As a result, Long Short Term Memory has been found to be superior to other models in providing highly accurate prediction results for demand forecasting based on advertising expenses. [ABSTRACT FROM AUTHOR]

• Based on the characteristics of different blood products, seasonal autoregressive integrated moving average with exogenous factors (SARIMAX) model (an extended model of ARIMA) and long short-term memory (LSTM) model were used to forecast daily demands of blood components. • The forecasting models, which predicts future demands of different blood components based on historical data, can help managers to overcome the challenges of blood stock control more effectively, thereby reducing blood waste and blood shortages. An adequate blood supply is an important guarantee for saving lives and protecting health. In order to manage the blood supply more effectively when the condition of demand and supply are uncertainty, it is very important to forecast the demands of blood resources. SARIMAX model and LSTM model were integrated into the prediction system of blood station. The collection and supply data of blood components was directly imported into the forecasting models to achieve automatic data update and model update. The forecasting daily demands of apheresis platelets, washing red blood cells (RBCs), suspended RBCs and plasma were recorded from January to June 2023 and compared with real data. The prediction models had good forecasting performances. In the goodness of fit results of apheresis platelet model, the maximum value of coefficient of determination (R2) could reach 87.6%, and the minimum value of the mean absolute percentage error (MAPE) was only 0.0037. The predicted data of washing RBCs could be basically fitted, and the MAPE was 0.0121. For the prediction of suspended RBCs, the R2 was greater than 66%, and the MAPE could be 0.0372. The plasma model generated very high goodness of fit results, with R2 of over 90% and the lowest MAPE of 0.0394. The forecasting models, which predicts future demands of different blood components based on historical data, can help managers to overcome the challenges of blood stock control more effectively, thereby reducing blood waste and blood shortages. [ABSTRACT FROM AUTHOR]

As agile processes are increasingly adopted for product design, and as consumer preferences are rapidly evolving with increasing information available from digital media, there is a need for a demand model that can accommodate the dynamics of product development. However, existing models of demand estimation, such as the discrete-choice models, do not capture the dynamics of product development and decision-making processes and thus are unable to effectively capture the effect of product updates and the release of information. To address this gap, we present a dynamic demand model and demonstrate how it can be used to determine the optimal time to release product updates. The demand model is based on decision field theory (DFT), which enables the modeling of the dynamic behavior of human decision makers. The contributions of this article are as follows. First, we formulate a computational model for demand modeling built on DFT and demonstrate the viability of using the model to determine product release strategies. Second, we provide analytical approximations of the demand model and compare the accuracy of the approximated demand against the demand predicted by the dynamics model. Third, we show an example of a game played by competitors trying to optimize demand for their products by choosing the optimal update time relative to each other. Finally, we demonstrate the feasibility of parameter estimation using only the demand data. [ABSTRACT FROM AUTHOR]

The rebalancing of bikes and demand prediction at the station level plays a fundamental role in the regular operation and maintenance of bike-sharing systems (BSSs). In this paper, a novel model which incorporates discrete wavelet transform (DWT), autoregressive integrated moving average (ARIMA), and long-short term memory neural network (LSTM NN), is proposed for BSS station-level check-in/out demand prediction. This study adopts the wavelet analysis method to denoise the raw BSS demand series firstly. Then, DWT is developed to decompose the denoised sequence into three high-frequency components (i.e. details) and one low-frequency component (i.e. approximation). ARIMA and LSTM are employed to forecast the detailed components and one approximation component, respectively. The predicted results of each model are reconstructed into the final outputs by DWT. An experiment on a real-world trip dataset showed that the proposed approach consistently outperforms the standard ARIMA model and LSTM model. [ABSTRACT FROM AUTHOR]

In the current era, the government consistently emphasizes the pursuit of high-quality development, as evidenced by the ongoing increase in the tertiary industry's GDP share. As a crucial component of the modern service sector, logistics plays a pivotal role in determining the operational efficiency and overall quality of the industrial economy. This study focuses on constructing a Chongqing logistics express demand prediction index system. It employs an improved BP neural network model to forecast the logistics express demand for Chongqing over the next five years. Given the limited express demand data sequence and the normalized characteristics of the data, the selected training method is the Bayesian regularization approach, with the LeCun Tanh function serving as the hidden layer activation function. Additionally, a genetic algorithm is designed to optimize the initial weights and thresholds of the BP neural network, thereby enhancing prediction accuracy and reducing the number of iterations. The experimental results of the improved GA-BP network are analyzed and compared, demonstrating that the improved BP neural network, utilizing GA optimization, can more reliably and accurately predict regional logistics express demand. According to the findings, the forecast indicates that the logistics express demand for Chongqing in 2026 will be 2,171,642,700 items. [ABSTRACT FROM AUTHOR]

In this study, we present a framework for optimizing pick-up and delivery operations in bike-sharing systems (BSSs), with particular emphasis on inventory rebalancing and vehicle routing to enhance operational efficiency. By employing a hybrid genetic algorithm (HGA), this study integrates sophisticated predictive models with multi-objective optimization techniques to strike a balance between operational efficiency and demand fulfillment in urban bike-share networks. For probabilistic demand forecasting, the DeepAR model is applied to a large number of bike stations clustered by geological proximity to enable stochastic inventory management. Our proposed HGA approach leverages both the genetic algorithm for generating feasible vehicle routes and mixed-integer programming for bike rebalancing to minimize travel distances while maintaining balanced inventory levels across all clustered stations. Through rigorous empirical evaluations, we demonstrate the effectiveness of our proposed methodology in improving service quality, thus making significant contributions to sustainable urban mobility. This study not only pushes the boundaries of theoretical knowledge in BSS logistics optimization but also offers managerial insights for practical implementation, particularly in densely populated urban settings. [ABSTRACT FROM AUTHOR]

Traditional revenue management systems are built under the assumption of independent demand per fare. The fare adjustment theory is a methodology to adjust fares that allows for the continued use of optimization algorithms and seat inventory control methods, even with the shift toward dependent demand. Since accurate demand forecasts are a key input to this methodology, it is reasonable to assume that for a scenario with uncertainties it may deliver suboptimal performance. Particularly, during and after COVID-19, airlines faced striking challenges in demand forecasting. This study demonstrates, firstly, the theoretical dominance of the fare adjustment theory under perfect conditions. Secondly, it lacks robustness to forecast errors. A Monte Carlo simulation replicating a revenue management system under mild assumptions indicates that a forecast error of ± 20 % can potentially prompt a necessity to adjust the margin employed in the fare adjustment theory by - 10 % . Moreover, a tree-based machine learning model highlights the forecast error as the predominant factor, with bias playing an even more pivotal role than variance. An out-of-sample study indicates that the predictive model steadily outperforms the fare adjustment theory. [ABSTRACT FROM AUTHOR]

Revenue management (RM) systems forecast demand and optimize prices to maximize a hotel's revenue. The RM function operates in coordination between a system and an analyst. Systems provide recommendations while analysts review the forecasts and prices to approve or make subjective adjustments. In many cases the recommendations are a "black box" with little insight regarding how recommendations are derived. This article proposes the k-Nearest Neighbor (k-NN) algorithm as a forecasting approach that can transition the "black box" to a "glass box." The benefits of the k-NN are discussed in detail and compared with neural networks. The analysis is conducted on 35 hotels in partnership with a leading RM service provider. The results indicate similar performance for both techniques, leading to an important discussion on model evaluation outside of accuracy. In particular, the article discusses some of the unique advantages k-NN provides for the RM discipline. [ABSTRACT FROM AUTHOR]

In a collaborative supply chain arrangement like vendor‐managed inventory, information on product demand at the point of sale is expected to be shared among members of the supply chain. However, in practice, obtaining such information can be costly, and some members may be unwilling or unable to provide the necessary access to the data. As such, large collaborative supply chains with multiple members may operate under a mixed‐information scenario where point‐of‐sale demand information is not known for all customers. Other sources of demand information exist and are becoming more available along supply chains using Industry 4.0 technologies and can serve as a substitute, but the data may be noisy, distorted, and partially missing. Under mixed information, leveraging existing customers' point‐of‐sale demand to improve the intermittent demand forecast of customers with missing information has yet to be explored. We propose a supervised demand forecasting method that uses multivariate time series clustering to map multiple sources of demand data. Members with missing downstream demand data have their resulting demand forecast improved by averaging over customers with similar delivery patterns for their final demand forecast. Our results show up to a 10% accuracy improvement over traditional intermittent demand forecasting methods with missing information. [ABSTRACT FROM AUTHOR]

In this paper, we introduce the mixed-frequency data model (MIDAS) to China's insurance demand forecasting. We select the monthly indicators Consumer Confidence Index (CCI), China Economic Policy Uncertainty Index (EPU), Consumer Price Index (PPI), and quarterly indicator Depth of Insurance (TID) to construct a Mixed Data Sampling (MIDAS) regression model, which is used to study the impact and forecasting effect of CCI, EPU, and PPI on China's insurance demand. To ensure forecasting accuracy, we investigate the forecasting effects of the MIDAS models with different weighting functions, forecasting windows, and a combination of forecasting methods, and use the selected optimal MIDAS models to forecast the short-term insurance demand in China. The experimental results show that the MIDAS model has good forecasting performance, especially in short-term forecasting. Rolling window and recursive identification prediction can improve the prediction accuracy, and the combination prediction makes the results more robust. Consumer confidence is the main factor influencing the demand for insurance during the COVID-19 period, and the demand for insurance is most sensitive to changes in consumer confidence. Shortly, China's insurance demand is expected to return to the pre-COVID-19 level by 2023Q2, showing positive development. The findings of the study provide new ideas for China's insurance policymaking. [ABSTRACT FROM AUTHOR]

Neural population responses in sensory systems are driven by external physical stimuli. This stimulus-response relationship is typically characterized by receptive fields, which have been estimated by neural system identification approaches. Such models usually require a large amount of training data, yet, the recording time for animal experiments is limited, giving rise to epistemic uncertainty for the learned neural transfer functions. While deep neural network models have demonstrated excellent power on neural prediction, they usually do not provide the uncertainty of the resulting neural representations and derived statistics, such as most exciting inputs (MEIs), from in silico experiments. Here, we present a Bayesian system identification approach to predict neural responses to visual stimuli, and explore whether explicitly modeling network weight variability can be beneficial for identifying neural response properties. To this end, we use variational inference to estimate the posterior distribution of each model weight given the training data. Tests with different neural datasets demonstrate that this method can achieve higher or comparable performance on neural prediction, with a much higher data efficiency compared to Monte Carlo dropout methods and traditional models using point estimates of the model parameters. At the same time, our variational method provides us with an effectively infinite ensemble, avoiding the idiosyncrasy of any single model, to generate MEIs. It allows to estimate the uncertainty of stimulus-response function, which we have found to be negatively correlated with the predictive performance at model level and may serve to evaluate models. Furthermore, our approach enables us to identify response properties with credible intervals and to determine whether the inferred features are meaningful by performing statistical tests on MEIs. Finally, in silico experiments show that our model generates stimuli driving neuronal activity significantly better than traditional models in the limited-data regime. Author summary: Neural system identification methods learn stimulus-response functions using experimental data to predict responses. These neuronal prediction models demand large amounts of training data, however, the recording time for each experiment is restricted, introducing the uncertainty about the neural features derived from trained models. Here, we present a Bayesian approach incorporating weight uncertainty to identify response functions and show that our method has higher or comparable predictive performance with a higher data efficiency compared to traditional methods using point estimates of model parameters. Additionally, our model provides an effective infinite ensemble to derive neural features, which avoid the idiosyncrasy of a single model. In this way, our method also allows us to estimate the uncertainty of the derived features and to conduct statistical tests on them. Generally, our Bayesian approach enables us to generate many similar stimuli to investigate biological information processing. [ABSTRACT FROM AUTHOR]

Microgrids have emerged as a promising solution for enhancing energy sustainability and resilience in localized energy distribution systems. Efficient energy management and accurate load forecasting are one of the critical aspects for improving the operation of microgrids. Various approaches for energy prediction and load forecasting using statistical models are discussed in the literature. In this work, a novel energy management framework that incorporates machine learning (ML) techniques is presented for an accurate prediction of solar and wind energy generation. The anticipated approach also emphasizes time series-based load forecasting in microgrids with precise estimation of State of Charge (SoC) of battery. A unique feature of the proposed framework is that utilizes historical load data and employs time series analysis coupled with different ML models to forecast the load demand in a commercial microgrids scenario. In this work, Long Short-Term Memory (LSTM) and Linear Regression (LR) models are employed for an experimental analysis to study the proposed framework under three different cases, such as (i) prediction of energy generation, (ii) load demand forecasting and, (iii) prediction of SoC of battery. The results show that the Random Forest (RF) and LSTM models performs well for energy prediction and load forecasting respectively. On the other hand, the Artificial Neural Network (ANN) model exhibited superior accuracy in terms of SoC estimation. Further, in this work, a Graphical User Interface (GUI) is developed for evaluating the efficacy of the proposed energy management framework. Article Highlights: Design of ML based framework for energy management system for commercial micro grids. Precise estimation of major sources of microgrids such as wind, solar and SoC of battery. A comparative study on various ML models with ANN model. An evaluation study for the efficiency of the proposed energy management framework by using real-time data incorporated GUI. [ABSTRACT FROM AUTHOR]

Electricity network operators undertake important responsibilities such as balancing electricity demand and supply, minimizing power outages, and making the necessary maintenance, repairs, and investments to provide safe and continuous energy. In this context, the most significant challenge encountered today is the need for a more immediate renewal of distribution grid expansion plans, owing to the rapid increase in energy demand and the grid integration of renewable energy power plants and electric vehicle charging stations. In order to find a solution to this issue, an active distribution network has been analyzed under five scenarios based on load demand forecasting. The artificial neural network method has been employed for the forecast of load demand, and the DigSilent Power Factory (DPF) model of the distribution network has been utilized to analyze the effects of scenarios. Connecting PV plants with capacities of 3 MW and 5 MW to different feeders in the distribution network, along with Hydrogen Energy Storage (HES) with a capacity of 1 MW to one feeder, has resulted in a reduction of the distribution transformer's occupancy rate from 79.8% to 70.6%. The contribution of a 1 MW HES system to the transformer occupancy rate was determined to be 1.3%. The results highlight the importance of considering the annual load demand forecast, as well as the network integration of PV power plants, electric vehicle charging stations, and hydrogen storage in grid expansion planning. • Load forecasting was made for feeders with the ANN model using the real load and meteorological data of the substation. • The grid model (power transformer, conductors, and demand load) was prepared in the DigSilent Power Factory (DPF) program. • The impact of HES, EV charging stations, and PV systems has been investigated in a grid expansion planning. • Grid expansion planning was analyzed through various scenarios considering load demand and load increase values. • The optimum placement and sizing of the DG were determined for the expansion planning of the distribution network. [ABSTRACT FROM AUTHOR]

This paper presents a traffic demand prediction method based on deep learning algorithms, aiming to address the dynamic traffic demands in satellite communication and enhance resource management efficiency. Integrating Seq2Seq and LSTM networks, the method improves prediction accuracy and applicability, especially for mobile terminals such as aviation and maritime ones. Unlike traditional approaches, it does not require extensive statistical data and can be generalized to real-world systems, providing stable long-term traffic demand predictions. This study utilizes real-world flight data mapped to corresponding satellite beams, allowing the precise prediction of beam-specific traffic demands. The results show that aggregating historical demand data for beams with similar trends achieves an average predictive Mean Squared Error (MSE) of 0.0007 and a maximum MSE fluctuation of 0.014, significantly outperforming predictions based on average values in terms of stability and accuracy. This novel solution for resource management in satellite communication ensures efficient and accurate long-term traffic demand predictions. [ABSTRACT FROM AUTHOR]

Rapid advancements in artificial intelligence (AI) are driving transformative changes in many areas, with significant environmental implications. Yet, environmental assessments for specific applications are scarce. This study presents an in‐depth life cycle assessment of “Foodforecast,” a machine learning (ML) cloud service designed to reduce food waste in bakeries by optimizing sales forecasting. It covers four impact categories: global warming, abiotic resource depletion, cumulative energy demand, and freshwater eutrophication. The assessment includes both the direct environmental impacts of the ML model and the underlying system hardware, as well as the indirect benefits of avoided bakery returns compared to traditional ordering methods, using real‐world case study data. In 2022, “Foodforecast” led to an average 30% reduction in bakery returns, primarily bread and rolls, according to sales reports. The associated environmental benefits significantly outweighed the system's direct impacts by one to three orders of magnitude across impact categories and return utilization scenarios. The study identifies support activities such as service maintenance during deployment as major direct impact factors, surpassing those from cloud compute for ML operations. Data processing and inference dominate the latter, while the much‐discussed ML training plays a minor role. The environmental consequences of AI are complex and dual sided. This case study demonstrates that AI might provide environmental benefits in certain contexts, yet results are constrained by methodological challenges and data uncertainties. There remains a need for further holistic LCAs across different ML applications to inform decision‐making processes and ultimately guide the responsible use of AI. [ABSTRACT FROM AUTHOR]

While there is huge demand for regional forecasts, information needed for selection of the most appropriate temporal and spatial scales is not available. The objective of this study is to demonstrate the basis of forecasting monthly mean rainfall over homogeneous regions by analyzing the forecasting skill and source of predictability. Reforecasts generated at the National Center for Medium Range Weather Forecasting (NCMRWF) for the period 1993–2015 using the coupled Unified Model are used in this study. Analysis of the forecasting skill over increasingly large lead times, averaging periods and spatial scales, is carried out to compare the skill at different time‐scales and to highlight the effect of spatial averaging over regions of coherent rainfall characteristics. Analysis of probabilistic forecasts is carried out to further demonstrate the usefulness of monthly mean forecasts. The influence of forcings on rainfall is studied both in model and in observations to understand the model's skill in representing interannual variability of monthly mean rainfall. Multiple regression analyses carried out for rainfall using climate indices as independent variables shows that the extent of forcings can largely explain the high variability of rainfall during the onset and withdrawal phase compared to the peak phase of monsoons. ENSO‐related subsidence is found to influence mainly the southern peninsular region, while tropical sea surface temperatures (SSTs) in the Indian Ocean are found to influence rainfall over northwest and central India by forcing circulation patterns typically associated with circumglobal teleconnections (CGTs) which are strongest during the month of June. Interestingly, the influence of CGTs on rainfall in the northeast is opposite to its influence on other homogeneous regions, which explains the contrast in influence of the North Indian Ocean SSTs on rainfall over the northeast and over All India. The model representation of influence of forcings and strength of teleconnections is better for specific region–month pairs, which is seen to influence the monthly variations in skill of forecasting rainfall over homogeneous regions. [ABSTRACT FROM AUTHOR]

Rapid growth rate indicates that the free-floating electric vehicle sharing (FFEVS) system leads to a new carsharing idea. Like other carsharing systems, the FFEVS system faces significant regional demand fluctuations. In such a situation, the rental stations and charging stations should be constructed in high-demand areas to reduce the scheduling costs. However, the planning of the FFEVS system includes a series of aspects of rental stations and charging stations, such as the location, size, and number, which interact with each other. In this paper, we first provide a method for forecasting the demand for car sharing based on the land characteristics of Beijing FFEVS station catchment areas. Then, the multi-objective MILP model for planning FFEVS systems is developed, which considers the requirements of vehicle relocation and electric vehicle charging. Afterward, the capabilities of the proposed models are demonstrated by the real data obtained from Beijing, China. Finally, the sensitivity analysis of the model is made based on varying demand and subsidy levels. From the results, the proposed model can provide decision-makers with useful insights about the planning of FFEVS systems, which bring great benefits to formulating more rational policies. [ABSTRACT FROM AUTHOR]

Local natural gas distribution companies (LDCs) require accurate demand forecasts across various time periods, geographic regions, and customer class hierarchies. Achieving coherent forecasts across these hierarchies is challenging but crucial for optimal decision making, resource allocation, and operational efficiency. This work introduces a method that structures the gas distribution system into cross-temporal hierarchies to produce accurate and coherent forecasts. We apply our method to a case study involving three operational regions, forecasting at different geographical levels and analyzing both hourly and daily frequencies. Trained on five years of data and tested on one year, our model achieves a 10% reduction in hourly mean absolute scaled error and a 3% reduction in daily mean absolute scaled error. [ABSTRACT FROM AUTHOR]

Effective solar energy utilization demands improvements in forecasting due to the unpredictable nature of solar irradiance (SI). This study introduces and rigorously tests two innovative forecasting models across different locations: the Sequential Deep Artificial Neural Network (SDANN) and the Deep Hybrid Random Forest Gradient Boosting (RFGB). SDANN, leveraging deep learning, aims to identify complex patterns in weather data, while RFGB, combining Random Forest and Gradient Boosting, proves more effective by offering a superior balance of efficiency and accuracy. The research highlights the SDANN model's deep learning capabilities along with the RFGB model's unique blend and their comparative success over existing models such as eXtreme Gradient Boosting (XGBOOST), Categorical Boosting (CatBOOST), Gated Recurrent Unit (GRU), and a K‐Nearest Neighbors (KNN) and XGBOOST hybrid. With the lowest Mean Squared Error (147.22), Mean Absolute Error (8.77), and a high R2 value (0.80) in a studied region, RFGB stands out. Additionally, detailed ablation studies on meteorological feature impacts on model performance further enhance accuracy and adaptability. By integrating cutting‐edge AI in SI forecasting, this research not only advances the field but also sets the stage for future renewable energy strategies and global policy‐making. [ABSTRACT FROM AUTHOR]

Demand response (DR) can decrease or increase energy consumption and has the ability to use generating assets more efficiently. Because of the increased power consumption, it has become necessary for the power system networks either to update or upgrade the already existing power system or to inculcate some schemes to minimize the load through effective customer engagement. To address this issue incentive-based demand response proved to be an effective tool to change the pattern of consumption. This work proposes a novel multilevel energy market considering coupon incentive based DR (C-IBDR). The proposed model is operated on a modified PJM 5-Bus system where the independent service operator (ISO) using economic dispatch (ED) computes the localized marginal pricing (LMP) and the load serving entity (LSE) issues coupons to consumers and procures the demand reduction from them. Two wind generators are incorporated into the test system and their effect on the localized marginal pricing with and without demand response is analyzed. The optimization problems are modeled using particle swarm optimization (PSO) and linear programming (LP) in MATLAB. The results demonstrate that the proposed C-IBDR reduces peak demand from 900 to 860 MW through the utilization of wind and DR. This alteration modifies the load curve, increases the power factor from 0.524 to 0.555, raises the revenue of LSEs from $106,646 to $106,946, reduces generation costs from $473,291 to $214,651, and procures a total of 262 MW of demand from the consumer side in the form of demand reduction. The system is further tested for scalability. The practicality of the suggested approach in handling more extensive systems is vividly demonstrated through its application to the modified IEEE 118-bus system. [ABSTRACT FROM AUTHOR]

Copyright of Tourism & Management Studies is the property of Escola Superior de Gestao, Hotelaria e Turismo, Universidade do Algarve and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Energy demand forecasting is crucial for effective resource management within the energy sector and is aligned with the objectives of Sustainable Development Goal 7 (SDG7). This study undertakes a comparative analysis of different forecasting models to predict future energy demand trends in Brazil, improve forecasting methodologies, and achieve sustainable development goals. The evaluation encompasses the following models: Seasonal Autoregressive Integrated Moving Average (SARIMA), Exogenous SARIMA (SARIMAX), Facebook Prophet (FB Prophet), Holt–Winters, Trigonometric Seasonality Box–Cox transformation, ARMA errors, Trend, and Seasonal components (TBATS), and draws attention to their respective strengths and limitations. Its findings reveal unique capabilities among the models, with SARIMA excelling in tracing seasonal patterns, FB Prophet demonstrating its potential applicability across various sectors, Holt–Winters adept at managing seasonal fluctuations, and TBATS offering flexibility albeit requiring significant data inputs. Additionally, the investigation explores the effect of external factors on energy consumption, by establishing connections through the Granger causality test and conducting correlation analyses. The accuracy of these models is assessed with and without exogenous variables, categorized as economical, industrial, and climatic. Ultimately, this investigation seeks to add to the body of knowledge on energy demand prediction, as well as to allow informed decision-making in sustainable energy planning and policymaking and, thus, make rapid progress toward SDG7 and its associated targets. This paper concludes that, although FB Prophet achieves the best accuracy, SARIMA is the most fit model, considering the residual autocorrelation, and it predicts that Brazil will demand approximately 70,000 GWh in 2033. [ABSTRACT FROM AUTHOR]

Inventory prediction is concerned with the forecasting of future demand for products in order to optimize inventory levels and supply chain management. The challenges include demand volatility, data quality, multi-dimensional interactions, lead time variability, seasonal trends, and dynamic pricing. Nevertheless, these models suffer from numerous shortcomings, and in this research, we propose a new model, MMCW-BiLSTM (modified multi-dimensional collaboratively wrapped BiLSTM), for inventory prediction. The MMCW-BiLSTM model reflects a considerable leap in inventory forecasting by combining a number of components in order to consider intricate temporal dependencies and incorporate feature interactions. The MMCW-BiLSTM makes use of BiLSTM layers, collaborative attention mechanisms, and a multi-dimensional attention approach to learn from augmented datasets consisting of the original features and the extracted time series data. Moreover, adding a Taylor series transformation allows for a more precise description of the features in the model, thus improving the prediction precision. The results show that the models make the least mistakes when they use the AV demand forecasting dataset, with MAE values of 1.75, MAPE values of 2.89, MSE values of 6.76, and RMSE values of 2.6. Similarly, when utilizing the product demand dataset, the model also achieves the lowest error values for these metrics at 1.97, 3.91, 8.76, and 2.96. Likewise, when utilizing the dairy goods sales dataset, the model also achieves the lowest error values for these metrics at 2.54, 3.69, 10.39, and 3.22. [ABSTRACT FROM AUTHOR]

Nowadays, due to the developments in technology and the effects of the pandemic, people have largely switched to e-commerce instead of traditional face-to-face commerce. In this sector, the product variety reaches tens of thousands, which has made it difficult to manage and to make quick decisions on inventory, promotion, pricing, and logistics. Therefore, it is thought that obtaining accurate and fast forecasting for the future will provide significant benefits to such companies in every respect. This study was built on the proposal of creating a cluster-based–genetic algorithm hybrid forecasting model including genetic algorithm (GA), cluster analysis, and some forecasting models as a new approach. In this study, unlike the literature, an attempt was made to create a more successful forecasting model for many products at the same time inside of single product forecasting. The proposed CBGA model success was compared separately to both the single prediction method successes and only genetic algorithm-based hybrid model successes by using real values from a popular B2C company. As a result, it has been observed that the forecasting success of the model proposed in this study is more successful than the forecasting made using single models or only the genetic algorithm. [ABSTRACT FROM AUTHOR]

This article provides an overview of the importance of evaluating forecasts and the current state of evaluating point forecasts. The main goal of evaluation is to monitor and improve the forecasting process. The article highlights the need to select the appropriate error measure, such as root mean squared error (RMSE), when evaluating forecasts. It also discusses the importance of scaling error measures when evaluating forecasts across different aggregations. The article suggests alternative approaches to the commonly used mean absolute percentage error (MAPE) and introduces concepts like root mean squared scaled error (RMSSE) and relative RMSE (rRMSE) for scaling error measures. Additionally, the article introduces the concept of forecast value added (FVA) as a way to compare different forecasting approaches. The author emphasizes the importance of accurately measuring and interpreting error measures in forecast evaluation. [Extracted from the article]

Predicting and understanding travellers' mode choices is crucial to developing urban transportation systems and formulating traffic demand management strategies. Machine learning (ML) methods have been widely used as promising alternatives to traditional discrete choice models owing to their high prediction accuracy. However, a significant body of ML methods, especially the branch of neural networks, is constrained by overfitting and a lack of model interpretability. This study employs a neural network with feature selection for predicting travel mode choices and Shapley additive explanations (SHAP) analysis for model interpretation. A dataset collected in Chengdu, China was used for experimentation. The results reveal that the neural network achieves commendable prediction performance, with a 12% improvement over the traditional multinomial logit model. Also, feature selection using a combined result from two embedded methods can alleviate the overfitting tendency of the neural network, while establishing a more robust model against redundant or unnecessary variables. Additionally, the SHAP analysis identifies factors such as travel expenditure, age, driving experience, number of cars owned, individual monthly income, and trip purpose as significant features in our dataset. The heterogeneity of mode choice behaviour is significant among demographic groups, including different age, car ownership, and income levels. [ABSTRACT FROM AUTHOR]