Search

In the field of risk assessment, the traditional econometric models are generally used to assess credit risk. And with the introduction of the "dual-carbon" goals to promote the development of a low-carbon economy, the scale of green credit in China has rapidly expanded. But with the advent of the big data era, due to the poor interpretability of a traditional single machine learning model, it is difficult to capture nonlinear relationships, and there are shortcomings in prediction accuracy and robustness. This paper selects the adjusted ensemble learning model based on the homogeneous and heterogeneous factors for user default prediction, which can efficiently process large quantities of high-dimensional data. This article adjusts each model to adapt to the task and innovatively compares various models. In this paper, the missing value filling method, feature selection, and ensemble model are studied and discussed, and the optimal ensemble model is obtained. When comparing the predictions of single models and ensemble models, the accuracy, sensitivity, specificity, F1-Score, Kappa, and MCC of Categorical Features Gradient Boosting (CatBoost) and Random undersampling Boosting (RUSBoost) all reach 100%. The experimental results prove that the algorithm based on adjusted homogeneous and heterogeneous ensemble learning can predict the user default efficiently and accurately. This paper also provides some references for establishing a risk assessment index system. [ABSTRACT FROM AUTHOR]

In stock trading, a common phenomenon is that the trends of stocks in the same industry are very similar. In contrast, the movements of stocks in different industries are often different. Therefore, applying the same model to all stock trading is inappropriate without distinguishing the industries in which the stocks belong. However, recommending an optimal industry stock trading model is very challenging based on performance evaluation indicators. First, the indicators of the trading model are diverse. Second, the ranking of multiple indicators is often inconsistent. In the paper, we model the problem to be solved as a multi-criteria decision-making process. Therefore, we first divide stock dataset into nine industries according to their main business. Then, we apply several machine learning algorithms as candidate models to generate trading signals. Second, we conduct daily trading backtesting based on the trading signals to obtain multiple performance evaluation indicators. Third, we propose an optimal recommendation algorithm for the industry stock trading model with TODIM. The experimental results in the US stock market and China's A-share market show that the proposed algorithm can get a better trading model out-of-sample industry stock. Moreover, we effectively evaluate the generalization ability of the algorithm based on the proposed metrics. Finally, the proposed long–short portfolios based on the algorithm have achieved returns exceeding the benchmark on most out-of-sample datasets. [ABSTRACT FROM AUTHOR]

Solving Rank Constrained Least Squares via Recursive Importance Sketching In statistics and machine learning, we sometimes run into the rank-constrained least squares problems, for which we need to find the best low-rank fit between sets of data, such as trying to figure out what factors are affecting the data, filling in missing information, or finding connections between different sets of data. This paper introduces a new method for solving this problem called the recursive importance sketching algorithm (RISRO), in which the central idea is to break the problem down into smaller, easier parts using a unique technique called "recursive importance sketching." This new method is not only easy to use, but it is also very efficient and gives accurate results. We prove that RISRO converges in a local quadratic-linear and quadratic rate under some mild conditions. Simulation studies also demonstrate the superior performance of RISRO. In this paper, we propose a recursive importance sketching algorithm for rank-constrained least squares optimization (RISRO). The key step of RISRO is recursive importance sketching, a new sketching framework based on deterministically designed recursive projections, and it significantly differs from the randomized sketching in the literature. Several existing algorithms in the literature can be reinterpreted under this new sketching framework, and RISRO offers clear advantages over them. RISRO is easy to implement and computationally efficient, and the core procedure in each iteration is to solve a dimension-reduced least squares problem. We establish the local quadratic-linear and quadratic rate of convergence for RISRO under some mild conditions. We also discover a deep connection of RISRO to the Riemannian Gauss–Newton algorithm on fixed rank matrices. The effectiveness of RISRO is demonstrated in two applications in machine learning and statistics: low-rank matrix trace regression and phase retrieval. Simulation studies demonstrate the superior numerical performance of RISRO. Funding: Y. Luo and A. Zhang were partially supported by the National Science Foundation [Grant CAREER-2203741]. W. Huang was partially supported by the Fundamental Research Funds for the Central Universities [Grant 20720190060] and the National Natural Science Foundation of China [Grant 12001455]. X. Li was partially supported by the National Natural Science Foundation of China [Grants 62141407 and 12271107], the Chenguang Program by the Shanghai Education Development Foundation and Shanghai Municipal Education Commission [Grant 19CG02], and the Shanghai Science and Technology Program [Grant 21JC1400600]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/opre.2023.2445. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is the most common cause of dementia. Accurate prediction and diagnosis of AD and its prodromal stage, i.e., mild cognitive impairment (MCI), is essential for the possible delay and early treatment for the disease. In this paper, we adopt the data from the China Longitudinal Aging Study (CLAS), which was launched in 2011, and includes a joint effort of 15 institutions all over the country. Four thousand four hundred and eleven people who are at least 60 years old participated in the project, where 3,514 people completed the baseline survey. The survey collected data including demographic information, daily lifestyle, medical history, and routine physical examination. In particular, we employ ensemble learning and feature selection methods to develop an explainable prediction model for AD and MCI. Five feature selection methods and nine machine learning classifiers are applied for comparison to find the most dominant features on AD/MCI prediction. The resulting model achieves accuracy of 89.2%, sensitivity of 87.7%, and specificity of 90.7% for MCI prediction, and accuracy of 99.2%, sensitivity of 99.7%, and specificity of 98.7% for AD prediction. We further utilize the SHapley Additive exPlanations (SHAP) algorithm to visualize the specific contribution of each feature to AD/MCI prediction at both global and individual levels. Consequently, our model not only provides the prediction outcome, but also helps to understand the relationship between lifestyle/physical disease history and cognitive function, and enables clinicians to make appropriate recommendations for the elderly. Therefore, our approach provides a new perspective for the design of a computer-aided diagnosis system for AD and MCI, and has potential high clinical application value. [ABSTRACT FROM AUTHOR]

With the increasing popularity of online foreign language teaching and learning practice, learners and teachers have developed a high demand for evaluation of teaching effectiveness. When we focus discussion on international Chinese teaching, which has been developed for a relatively short time and not experienced enough, online teaching effectiveness evaluation has become an important obstacle to the development of teaching. This paper introduces a hybrid technique based on fuzzy evaluation method, for determining and suggesting possible types of errors in international Chinese online listening and speaking instruction and giving suggestions for improvement. The system can help learners to identify and determine the types of errors in Chinese listening and speaking learning in a timely manner and make a more objective and comprehensive evaluation of learning performance; at the same time, it helps teachers to trace the effectiveness of teaching design and implementation in a targeted manner and make corresponding scientific decisions. This hybrid technology combines existing language teaching evaluation models, takes advantage of data from online education, and creates corresponding criteria through machine learning fuzzy algorithms and large data sample training, combined with the theory of effective teaching evaluation, which is beneficial for all participants of online Chinese listening and speaking teaching to improve their learning effectiveness. [ABSTRACT FROM AUTHOR]

There are many thyroid diseases affecting people all over the world. Many diseases affect the thyroid gland, like hypothyroidism, hyperthyroidism, and thyroid cancer. Thyroid inefficiency can cause severe symptoms in patients. Effective classification and machine learning play a significant role in the timely detection of thyroid diseases. This timely classification will indeed affect the timely treatment of the patients. Automatic and precise thyroid nodule detection in ultrasound pictures is critical for reducing effort and radiologists' mistake rate. Medical images have evolved into one of the most valuable and consistent data sources for machine learning generation. In this paper, various machine learning algorithms like decision tree, random forest algorithm, KNN, and artificial neural networks on the dataset create a comparative analysis to better predict the disease based on parameters established from the dataset. Also, the dataset has been manipulated for accurate prediction for the classification. The classification was performed on both the sampled and unsampled datasets for better comparison of the dataset. After dataset manipulation, we obtained the highest accuracy for the random forest algorithm, equal to 94.8% accuracy and 91% specificity. [ABSTRACT FROM AUTHOR]

With the prosperity of e-commerce, ordering food online has become increasingly prevalent nowadays. Derived from the dispatching problem in Meituan, a real online food delivery (OFD) platform in China, this paper addresses an OFD problem (OFDP). To solve the OFDP efficiently, an effective matching algorithm with adaptive tie-breaking strategy (MAATS) is proposed by collaboratively fusing the optimization methods with machine learning (ML) techniques. First, to efficiently generate a partial solution with a certain quality, a best-matching heuristic is proposed. Second, to break the ties occurring in the best-matching heuristic and obtain a complete solution with high quality, multiple tie-breaking operators are designed. Third, to adapt to different scenarios, the tie-breaking operators are utilized in a dynamic way which is achieved by using ML methods including decision trees and a specially-designed deep neural network. Fourth, problem-specific features are extracted as decision information to assist the ML models to predict the best tie-breaking operator for use in the current scenario. Preliminary offline simulations are carried out on real historical data sets to validate the effectiveness of the proposed algorithm. Moreover, rigorous online A/B tests are conducted to evaluate the performance of MAATS in practical applications. The results of offline and online tests demonstrate both the effectiveness of MAATS to solve the OFDP and the application value to improve customer satisfaction and delivery efficiency on Meituan platform. [ABSTRACT FROM AUTHOR]

With the rapid development of social media, people can access a large amount of data in a short period of time, and big data technology has emerged. With the vigorous development of cloud computing and big data, the method of mining audience interests through a large amount of data to guide film and television creation has attracted more and more attention from experts and scholars. In order to understand the current situation of film and television drama creation in China and provide suggestions for the shortcomings in the industry, this article mainly analyzes the application of intelligent algorithms for traffic prediction models and big data analysis in film and television creation. This intelligent algorithm can predict the potential audience of movies or TV dramas, helping producers and investors make decisions. This system utilizes artificial intelligence technology to select suitable actors for characters based on their matching degree and past work performance. This article applies intelligent algorithms to big data processing to improve the accuracy of data processing. This article explores the application of intelligent algorithms and big data analysis in film and television creation. Using machine learning algorithms to predict the potential audience of a movie or TV series based on historical data, providing decision-making basis for investors and producers. This system utilizes AI technology to select suitable actors for characters based on their matching degree with characters and past work performance, improving the scientific and accurate selection of roles. The application of these technologies helps to improve production efficiency and quality, reduce costs and risks, and inject new impetus into the sustainable development of the film and television industry. [ABSTRACT FROM AUTHOR]

Background: Dento-maxillofacial deformities are common problems. Orthodontic–orthognathic surgery is the primary treatment but accurate diagnosis and careful surgical planning are essential for optimum outcomes. This study aimed to establish and verify a machine learning–based decision support system for treatment of dento-maxillofacial malformations. Methods: Patients (n = 574) with dento-maxillofacial deformities undergoing spiral CT during January 2015 to August 2020 were enrolled to train diagnostic models based on five different machine learning algorithms; the diagnostic performances were compared with expert diagnoses. Accuracy, sensitivity, specificity, and area under the curve (AUC) were calculated. The adaptive artificial bee colony algorithm was employed to formulate the orthognathic surgical plan, and subsequently evaluated by maxillofacial surgeons in a cohort of 50 patients. The objective evaluation included the difference in bone position between the artificial intelligence (AI) generated and actual surgical plans for the patient, along with discrepancies in postoperative cephalometric analysis outcomes. Results: The binary relevance extreme gradient boosting model performed best, with diagnostic success rates > 90% for six different kinds of dento-maxillofacial deformities; the exception was maxillary overdevelopment (89.27%). AUC was > 0.88 for all diagnostic types. Median score for the surgical plans was 9, and was improved after human–computer interaction. There was no statistically significant difference between the actual and AI- groups. Conclusions: Machine learning algorithms are effective for diagnosis and surgical planning of dento-maxillofacial deformities and help improve diagnostic efficiency, especially in lower medical centers. [ABSTRACT FROM AUTHOR]

Scientific analyses of urban flood risks are essential for evaluating urban flood insurance and designing drainage projects. Although the current rainfall monitoring system in China has a dense station network and high-precision rainfall data, the time series is short. In contrast, historical rainfall data have a longer sample time series but lower precision. This study introduced a PCA algorithm to reconstruct historical rainfall data. Based on the temporal and spatial characteristics of rainfall extracted from high-resolution rainfall data over the past decade, historical (6 h intervals) rainfall spatial data were reconstructed into high-resolution (1 h intervals) spatial data to satisfy the requirements of the urban flood risk analysis. The results showed that the average error between the reconstructed data and measured values in the high-value area was within 15% and in the low-value area was within 20%, representing decreases of approximately 65% and 40%, respectively, compared to traditional interpolation data. The reconstructed historical spatial rainfall data conformed to the temporal and spatial distribution characteristics of rainfall, improved the granularity of rainfall spatial data, and enabled the effective and reasonable extraction and summary of the fine temporal and spatial distribution characteristics of rainfall. [ABSTRACT FROM AUTHOR]

Recently, carbon price forecasting has become critical for financial markets and environmental protection. Due to their dynamic, nonlinear, and high noise characteristics, predicting carbon prices is difficult. Machine learning forecasting often uses stacked ensemble algorithms. As a result, common stacking has many limitations when applied to time series data, as its cross-validation process disrupts the temporal sequentiality of the data. Using a double sliding window scheme, we proposed an improved stacking ensemble algorithm that avoided overfitting risks and maintained temporal sequentiality. We replaced cross-validation with walk-forward validation. Our empirical experiment involved the design of two dynamic forecasting frameworks utilizing the improved algorithm. This incorporated forecasting models from different domains as base learners. We used three popular machine learning models as the meta-model to integrate the predictions of each base learner, further narrowing the gap between the final predictions and the observations. The empirical part of this study used the return of carbon prices from the Shenzhen carbon market in China as the prediction target. This verified the enhanced accuracy of the modified stacking algorithm through the use of five statistical metrics and the model confidence set (MCS). Furthermore, we constructed a portfolio to examine the practical usefulness of the improved stacking algorithm. Empirical results showed that the improved stacking algorithm could significantly and robustly improve model prediction accuracy. Support vector machines (SVR) aggregated results better than the other two meta-models (Random forest and XGBoost) in the aggregation step. In different volatility states, the modified stacking algorithm performed differently. We also found that aggressive investment strategies can help investors achieve higher investment returns with carbon option assets. [ABSTRACT FROM AUTHOR]

The quality of talent has increased across all fields due to the constant growth of different industries and the growing job saturation. Real-time job information on recruitment platforms can, therefore, accurately reflect the demand for talent from businesses, serving as a basis for the creation of training policies in schools. In international competition, the development of talents, especially top-level talents, will become more and more crucial. Growing in importance is China's economy and social development. The evaluation of higher vocational and technical talents, however, should also be assessed from a variety of angles, given the diversification of talent training objectives and teaching methods, as well as the expansion of teaching functions. An emerging machine learning technology called deep learning (DL) has been developed to bring machine learning closer to the goals of artificial intelligence. This essay offers a thorough evaluation of the depth of deep learning as it relates to the development of innovative talent in schools. The entire school must be strengthened. It is demonstrated that the average execution time is slashed by 0.0024 s, and the learning sample size error of the DL model is reduced by 0.05276 when compared to the Apriori method. As a result, implementing and researching the DL model can significantly improve both the overall teaching quality of schools and their capacity for innovation. [ABSTRACT FROM AUTHOR]

The reverse transcription-quantitative polymerase chain reaction (RT-qPCR) approach has been widely used to detect the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). However, instead of using it alone, clinicians often prefer to diagnose the coronavirus disease 2019 (COVID-19) by utilizing a combination of clinical signs and symptoms, laboratory test, imaging measurement (e.g., chest computed tomography scan), and multivariable clinical prediction models, including the electronic nose. Here, we report on the development and use of a low cost, noninvasive method to rapidly sniff out COVID-19 based on a portable electronic nose (GeNose C19) integrating an array of metal oxide semiconductor gas sensors, optimized feature extraction, and machine learning models. This approach was evaluated in profiling tests involving a total of 615 breath samples composed of 333 positive and 282 negative samples. The samples were obtained from 43 positive and 40 negative COVID-19 patients, respectively, and confirmed with RT-qPCR at two hospitals located in the Special Region of Yogyakarta, Indonesia. Four different machine learning algorithms (i.e., linear discriminant analysis, support vector machine, stacked multilayer perceptron, and deep neural network) were utilized to identify the top-performing pattern recognition methods and to obtain a high system detection accuracy (88–95%), sensitivity (86–94%), and specificity (88–95%) levels from the testing datasets. Our results suggest that GeNose C19 can be considered a highly potential breathalyzer for fast COVID-19 screening. [ABSTRACT FROM AUTHOR]

The accurate prediction of surface settlement caused by large-diameter shield tunneling is crucial for the safety of the tunnel environment. However, due to the complexity and uncertainty of the rock-machine interaction and groundwater variation, it is difficult to predict the settlement by developing traditional theoretical methods. Recently, a big number of data obtained from the Chunfeng shield tunnel in China provides the possibility to predict the settlement using machine-learning methods. In this study, the equipment parameters, the geological parameters, and the monitored settlements are used to establish the models. Three machine-learning algorithms (i.e., long-short-term memory (LSTM), random forest (RF), and gated recurrent unit (GRU)) are used to predict the surface settlement. Three indicators, mean absolute error (MAE), accuracy (ACC), and coefficient of determination ( R 2 ), are selected to evaluate the prediction performance. Results demonstrated that the filtering and selection of model parameters is vitally important to the accuracy of model prediction. Among the three machine-learning algorithms, the LSTM algorithm gives the best accuracy in predicting the maximum surface settlement and can effectively predict the settlement development in different strata. [ABSTRACT FROM AUTHOR]

Deriving large-scale and high-quality precipitation products from satellite remote-sensing spectral data is always challenging in quantitative precipitation estimation (QPE), and limited studies have been conducted even using China's latest Fengyun-4A (FY-4A) geostationary satellite. Taking three rainstorm events over South China as examples, a machine-learning-based regression model was established using the random forest (RF) method to derive QPE from FY-4A observations, in conjunction with cloud parameters and physical quantities. The cross-validation results indicate that both daytime (DQPE) and nighttime (NQPE) RF algorithms performed well in estimating QPE, with the bias score, correlation coefficient and root-mean-square error of DQPE (NQPE) of 2.17 (2.42), 0.79 (0.83) and 1.77 mmh-1 (2.31 mmh-1), respectively. Overall, the algorithm has a high accuracy in estimating precipitation under the heavy-rain level or below. Nevertheless, the positive bias still implies an overestimation of precipitation by the QPE algorithm, in addition to certain misjudgements from non-precipitation pixels to precipitation events. Also, the QPE algorithm tends to underestimate the precipitation at the rainstorm or even above levels. Compared to single-sensor algorithms, the developed QPE algorithm can better capture the spatial distribution of land-surface precipitation, especially the centre of strong precipitation. Marginal difference between the data accuracy over sites in urban and rural areas indicate that the model performs well over space and has no evident dependence on landscape. In general, our proposed FY-4A QPE algorithm has advantages for quantitative estimation of summer precipitation over East Asia. [ABSTRACT FROM AUTHOR]

Large volumes of data have been accumulated in identical or very similar contexts of decision making. To generate accurate and explanatory decision recommendations by using these data, this paper proposes a data-driven multi-criteria decision making (MCDM) method based on machine learning (ML) algorithms and the evidential reasoning (ER) approach. In the method, based on the assessments of all historical alternatives, a comparison framework is designed to determine the most appropriate ML algorithm with the highest predictive accuracy. An optimization model is then constructed to connect the appropriate ML algorithm with the ER approach. Through the optimization model, the difference between overall assessments derived from the ER approach and the predicted results derived from the appropriate ML algorithm is minimized to learn criterion weights. The learned criterion weights are used to generate accurate and explanatory decisions. Such a combination takes advantage of high predictability of ML algorithms and favorable interpretability of the ER approach simultaneously. To demonstrate the validity and applicability of the proposed method, it is used to aid the diagnosis of thyroid nodules for a tertiary hospital located in Hefei, Anhui, China. Its merits are further highlighted by its comparison with two traditional ER approaches and the appropriate ML algorithm. • Data-driven decision making based on ER approach and ML algorithms is proposed. • ML algorithms are compared based on their linkage with ER approach. • An optimization model is constructed to make explanatory decisions based on ML. • The proposed method is used to help radiologists diagnose thyroid nodules. • The proposed method is compared with decision making learning from accuracy and AUC. [ABSTRACT FROM AUTHOR]

The spatial decomposition of demographic data at a fine resolution is a classic and crucial problem in the field of geographical information science. The main objective of this study was to compare twelve well-known machine learning regression algorithms for the spatial decomposition of demographic data with multisource geospatial data. Grid search and cross-validation methods were used to ensure that the optimal model parameters were obtained. The results showed that all the global regression algorithms used in the study exhibited acceptable results, besides the ordinary least squares (OLS) algorithm. In addition, the regularization method and the subsetting method were both useful for alleviating overfitting in the OLS model, and the former was better than the latter. The more competitive performance of the nonlinear regression algorithms than the linear regression algorithms implies that the relationship between population density and influence factors is likely to be non-linear. Among the global regression algorithms used in the study, the best results were achieved by the k-nearest neighbors (KNN) regression algorithm. In addition, it was found that multi-sources geospatial data can improve the accuracy of spatial decomposition results significantly, and thus the proposed method in our study can be applied to the study of spatial decomposition in other areas. [ABSTRACT FROM AUTHOR]

The accurate monitoring of forest cover and its changes are essential for environmental change research, but current satellite products for forest coverage carry many uncertainties. This study used 30-m Landsat-8 data, and aggregated 1-m GaoFen-2 (GF-2) satellite images to construct the training samples and used multiple machine learning algorithms (MLAs) to estimate the fractional forest cover (FFC) in China's Three North Region (TNR). In this study, multiple MLAs were merged to construct stacked generalization (SG) models based on the idea of SG, and the performances of the MLAs in the FFC estimation were evaluated. The results of the 10-fold cross-validation showed that all non-linear algorithms had a good performance, with an R2 value of greater than 0.8 and a root-mean square error (RMSE) of less than 0.05. In the bagging ensemble, the random forest (RF) (R2 = 0.993, RMSE = 0.020) model performed the best and in the boosting ensemble, the light gradient boosted machine (LGBM) (R2 = 0.992, RMSE = 0.022) performed the best. Although the evaluation index of the RF is slightly better than that of the LGBM, the independent validation results show that the two models have similar performances. The model evaluation results of the independent datasets showed that, in the SG model, the performance of the SG(LGBM) (R2 = 0.991, RMSE = 0.034) was better than that of the single or non-ensemble model. Comparing the FFC estimates of our model with those of existing datasets showed that our model exhibited more forest spatial distribution details and higher accuracy in complex landscapes. Overall, in this study, the method of using high-resolution remote sensing (RS) images to extract samples for FFC estimation is feasible. Our results demonstrate the potential of the ensemble MLAs to map the FFC. The research results also show that among many MALs, the RF algorithm is the most suitable algorithm for estimating FFC, which provides a reference for future research. [ABSTRACT FROM AUTHOR]