Search

Purpose: This paper aims to identify, prioritise and explore the relationships between the various barriers that are hindering the machine learning (ML) adaptation for analysing accident data information in the Indian petroleum industry. Design/methodology/approach: The preferred reporting items for systematic reviews and meta-analysis (PRISMA) is initially used to identify key barriers as reported in extant literature. The decision-making trial and evaluation laboratory (DEMATEL) technique is then used to discover the interrelationships between the barriers, which are then prioritised, based on three criteria (time, cost and relative importance) using complex proportional assessment (COPRAS) and multi-objective optimisation method by ratio analysis (MOORA). The Delphi method is used to obtain and analyse data from 10 petroleum experts who work at various petroleum facilities in India. Findings: The findings provide practical insights for management and accident data analysts to use ML techniques when analysing large amounts of data. The analysis of barriers will help organisations focus resources on the most significant obstacles to overcome barriers to adopt ML as the primary tool for accident data analysis, which can save time, money and enable the exploration of valuable insights from the data. Originality/value: This is the first study to use a hybrid three-phase methodology and consult with domain experts in the petroleum industry to rank and analyse the relationship between these barriers. [ABSTRACT FROM AUTHOR]

Purpose: In India, one of the prime focuses of a post-graduate management program is to prepare students and make them job-ready. Masters in Business Management (MBA) program helps students to imbibe theoretical and practical skills which are required by the industry, which can make them hit the ground running from the day they start their career. Many students (almost 40–50%) get pre-placement offers based on their performance in summer internship. The selection for summer interns by the corporate happens within a few months of the student joining the MBA program. Signaling theory in education indicates that the level of productivity of an individual is independent of education, but the educational qualification acts as a testimony for higher ability. However, this theory does not explain the reason for the mismatch between "education and work" or "education and the disparity in salary" between individuals who earn differently but have the same qualification. The paper aims to explore three attributes namely – "employability"– the chance of being employable; "pre-placement offers" – the chance of securing a job offer based on the performance in internship and "salary" – the chance of bagging a good job offer with a high salary. Design/methodology/approach: The authors have used longitudinal data consisting of 1,202 students who graduated from reputable business schools (B-Schools) in India. In the study, the authors have used predictive analytics on six years data set that have been gathered. The authors have considered 24 attributes including educational background at the graduate level (BE, B Tech, B Com, BSc, BBA and others), score secured in class ten (high, medium and low), score secured in class twelve (high, medium and low), score secured in graduation (high, medium and low), competency in soft skills (high, medium and low), participation in co-curricular activities (high, medium and low) and social engagement status (high, medium and low). Findings: The findings of the study contradict the signaling theory in education. The findings suggest that the educational qualification alone cannot be the predictor of the employability and the salary offered to the student. The authors note that the better performance at a lower level of qualification (class 12) is the strong predictor in comparison to the student performance at their graduation and post-graduation level. The authors further observed at the post-graduate management education level that soft skills and participation in co-curricular activities are the major deciding factors to predict employability and pre-placement job opportunity and marks secured in class 12 is one more factor that gets added to this list to predict salary. The paper can immensely help management graduates to focus on key aspects that can help to hone appropriate skills and also can help management institutions to select the right students for management programs. Research limitations/implications: The analysis and the predictive model may apply to Indian B-Schools wherein the quality of students are almost the same or better. Predictive analytics has been used to explain the employability of management graduates alone and not any other. Practical implications: The authors' study might be useful for those students who often fail to understand "what" skills are the most important predictors of their performance in the pre-placement and final-placement interviews. Moreover, the study may serve as a useful guide to those organizations that often face dilemmas to understand "how" to select an ideal candidate for the particular job profile from a campus. Originality/value: The authors believe that the current study is one of the few studies that have attempted to examine the employability of management graduates using predictive analytics. The study further contradicts that the signaling theory in education does not help better explain the employability of the students in extremely high-paced business environments. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to explore and evaluate the existing and future impact of artificial intelligence (AI) and machine learning on the global economy. It includes viewing the inclusion of AI in different sectors, its impact on industries, the trends of the forerunning companies that are capitalizing on AI and the idea of crystalizing exponential growth while maintaining a balance between the understanding of humans and the subsequent possibilities of AI. Design/methodology/approach: This paper is based on secondary research, reviewing literature based on different industries and perspectives. Findings: The global potential of AI is exponential; the development of AI should be effective. Globally, we see contrasting views, defining the consequences of AI. Hence, the balance between humans and AI, protocols and a global regulatory system needs to be established to prevent catastrophic results soon. Practical implications: The benefits of AI are enormous. The rising incorporation of AI must take into consideration the basic safety fundamentals for a better future. Social implications: This paper will enable readers to understand the importance of AI in the global economy, its current involvement in major industries and the subsequent need for balance in technology. Originality/value: This conceptual review is by its nature and original contribution and, specifically, an interpretation for India. [ABSTRACT FROM AUTHOR]

Purpose: The rapid urbanization of Indian cities and the population surge in cities has steered a massive demand for energy, thereby increasing the carbon emissions in the environment. Information and technology advancements, aided by predictive tools, can optimize this energy demand and help reduce harmful carbon emissions. Out of the multiple factors governing the energy consumption and comfort of buildings, indoor room temperature is a critical one, as it envisages the need for regulating the temperature. This paper aims to propose a mathematical model for short-term forecasting of indoor room temperature in the Indian context to optimize energy consumption and reduce carbon emissions in the environment. Design/methodology/approach: A study is conducted to forecast the indoor room temperature of an Indian corporate building structure, based upon various external environmental factors: temperature and rainfall and internal factors like cooling control, occupancy behavior and building characteristics. Expert insight and principal component analysis are applied for appropriate variables selection. The machine learning approach using Box–Jenkins time series models is used for the forecasting of indoor room temperature. Findings: ARIMAX model, with lagged forecasted and explanatory variables, is found to be the best-fit model. A predictive short-term hourly temperature forecasting model is developed based upon ARIMAX model, which yields fairly accurate results for data set pertaining to the building conditions and climatic parameters in the Indian context. Results also investigate the relationships between the forecasted and individual explanatory variables, which are validated using theoretical proofs. Research limitations/implications: The models considered in this research are Box–Jenkins models, which are linear time series models. There are non-linear models, such as artificial neural network models and deep learning models, which can be a part of this study. The study of hybrid models including combined forecasting techniques comprising linear and non-linear methods is another important area for future scope of study. As this study is based on a single corporate entity, the models developed need to be tested further for robustness and reliability. Practical implications: Forecasting of indoor room temperature provides essential practical information about meeting the in-future energy demand, that is, how much energy resources would be needed to maintain the equilibrium between energy consumption and building comfort. In addition, this forecast provides information about the prospective peak usage of air-conditioning controls within the building indoor control management system through a feedback control loop. The resultant model developed can be adopted for smart buildings within Indian context. Social implications: This study has been conducted in India, which has seen a rapid surge in population growth and urbanization. Being a developing country, India needs to channelize its energy needs judiciously by minimizing the energy wastage and reducing carbon emissions. This study proposes certain pre-emptive measures that help in minimizing the consumption of available energy resources as well as reducing carbon emissions that have significant impact on the society and environment at large. Originality/value: A large number of factors affecting the indoor room temperature present a research challenge for model building. The paper statistically identifies the parameters influencing the indoor room temperature forecasting and their relationship with the forecasted model. Considering Indian climatic, geographical and building structure conditions, the paper presents a systematic mathematical model to forecast hourly indoor room temperature for next 120 h with fair degree of accuracy. [ABSTRACT FROM AUTHOR]

Purpose: Data envelopment analysis (DEA) has wide applications in the agricultural sector to evaluate the efficiency with crisp input and output data. However, in agricultural production, impreciseness and uncertainty in data are common. As a result, the data obtained from farmers vary. This impreciseness in crisp data can be represented in fuzzy sets. This paper aims to employ a combination of fuzzy data envelopment analysis (FDEA) approach to yield crisp DEA efficiency values by converting the fuzzy DEA model into a linear programming problem and machine learning algorithms for better evaluation and prediction of the variables affecting the farm efficiency. Design/methodology/approach: DEA applications are focused on the use of a common two-step approach to find crucial factors that affect efficiency. It is important to identify impactful variables for minimizing production adversities. In this study, first, FDEA was applied for efficiency estimation and ranking of the paddy growers. Second, the support vector machine (SVM) and random forest (RF) were used for identifying the key leading factors in efficiency prediction. Findings: The proposed research was conducted with 450 paddy growers. In comparison to the general DEA approach, the FDEA model evaluates fuzzy DEA efficiency giving the user the flexibility to measure the performance at different possibility levels. Originality/value: The use of machine learning applications introduces advanced strategies and important factors influencing agricultural production, which may help future research in farms' performance. [ABSTRACT FROM AUTHOR]

Purpose: Any business that opts to adopt a recommender engine (RE) for various potential benefits must choose from the candidate solutions, by matching to the task of interest and domain. The purpose of this paper is to choose RE that fits best from a set of candidate solutions using rule-based automated machine learning (ML) approach. The objective is to draw trustworthy conclusion, which results in brand building, and establishing a reliable relation with customers and undeniably to grow the business. Design/methodology/approach: An experimental quantitative research method was conducted in which the ML model was evaluated with diversified performance metrics and five RE algorithms by combining offline evaluation on historical and simulated movie data set, and the online evaluation on business-alike near-real-time data set to uncover the best-fitting RE. Findings: The rule-based automated evaluation of RE has changed the testing landscape, with the removal of longer duration of manual testing and not being comprehensive. It leads to minimal manual effort with high-quality results and can possibly bring a new revolution in the testing practice to start a service line "Machine Learning Testing as a service" (MLTaaS) and the possibility of integrating with DevOps that can specifically help agile team to ship a fail-safe RE evaluation product targeting SaaS (software as a service) or cloud deployment. Research limitations/implications: A small data set was considered for A/B phase study and was captured for ten movies from three theaters operating in a single location in India, and simulation phase study was captured for two movies from three theaters operating from the same location in India. The research was limited to Bollywood and Ollywood movies for A/B phase, and Ollywood movies for simulation phase. Practical implications: The best-fitting RE facilitates the business to make personalized recommendations, long-term customer loyalty forecasting, predicting the company's future performance, introducing customers to new products/services and shaping customer's future preferences and behaviors. Originality/value: The proposed rule-based ML approach named "2-stage locking evaluation" is self-learned, automated by design and largely produces time-bound conclusive result and improved decision-making process. It is the first of a kind to examine the business domain and task of interest. In each stage of the evaluation, low-performer REs are excluded which leads to time-optimized and cost-optimized solution. Additionally, the combination of offline and online evaluation methods offer benefits, such as improved quality with self-learning algorithm, faster time to decision-making by significantly reducing manual efforts with end-to-end test coverage, cognitive aiding for early feedback and unattended evaluation and traceability by identifying the missing test metrics coverage. [ABSTRACT FROM AUTHOR]

Purpose: This study aims to analyse the systemic risk emitted by all publicly listed commercial banks in a key emerging economy, India. Design/methodology/approach: The study makes use of the Tobias and Brunnermeier (2016) estimator to quantify the systemic risk (ΔCoVaR) that banks contribute to the system. The methodology addresses a classification problem based on the probability that a particular bank will emit high systemic risk or moderate systemic risk. The study applies machine learning models such as logistic regression, random forest (RF), neural networks and gradient boosting machine (GBM) and addresses the issue of imbalanced data sets to investigate bank's balance sheet features and bank's stock features which may potentially determine the factors of systemic risk emission. Findings: The study reports that across various performance matrices, the authors find that two specifications are preferred: RF and GBM. The study identifies lag of the estimator of systemic risk, stock beta, stock volatility and return on equity as important features to explain emission of systemic risk. Practical implications: The findings will help banks and regulators with the key features that can be used to formulate the policy decisions. Originality/value: This study contributes to the existing literature by suggesting classification algorithms that can be used to model the probability of systemic risk emission in a classification problem setting. Further, the study identifies the features responsible for the likelihood of systemic risk. [ABSTRACT FROM AUTHOR]

Purpose: This study aims to examine the technical efficiency of the chemical-free farming system in India using a hybrid combination of data envelopment analysis (DEA) and machine learning (ML) approaches. Design/methodology/approach: The study used a two-stage approach. In the first stage, the efficiency scores of decision-making units' efficiency (DMUs) are obtained using an input-oriented DEA model under the assumption of a variable return to scale. Based on these scores, the DMUs are classified into efficient and inefficient categories. The 2nd stage of analysis involves the identification of the most important predictors of efficiency using a random forest model and a generalized logistic regression model. Findings: The results show that by using their resources efficiently, growers can reduce their inputs by 34 percent without affecting the output. Orchard's size, the proportion of land, grower's age, orchard's age and family labor are the most important determinants of efficiency. Besides, growers' main occupation and footfall of intermediaries at the farm gate also demonstrate significant influence on efficiency. Research limitations/implications: The study used only one output and a limited set of input variables. Incorporating additional variables or dimensions like fertility of the land, climatic conditions, altitude of the land, output quality (size/taste/appearance) and per acre profitability could yield more robust results. Although pineapple is cultivated in all eight northeastern states, the data for the study has been collected from only two states. The production and marketing practices followed by the growers in the remaining six northeastern states and other parts of the country might be different. As the growers do not maintain farm records, their data might suffer from selective retrieval bias. Practical implications: Given the rising demand for organic food, improving the efficiency of chemical-free growers will be a win-win situation for both growers and consumers. The results will aid policymakers in bringing necessary interventions to make chemical-free farming more remunerative for the growers. The business managers can act as a bridge to connect these remote growers with the market by sharing customer feedback and global best practices. Social implications: Although many developments have happened to the DEA technique, the present study used a traditional form of DEA. Therefore, future research should combine ML techniques with more advanced versions like bootstrap and fuzzy DEA. Upcoming research should include more input and output variables to predict the efficiency of the chemical-free farming system. For instance, environmental variables, like climatic conditions, degree of competition, government support and consumers' attitude towards chemical-free food, can be examined along with farm and grower-specific variables. Future studies should also incorporate chemical-free growers from a wider geographic area. Lastly, future studies can also undertake a longitudinal estimation of efficiency and its determinants for the chemical-free farming system. Originality/value: No prior study has used a hybrid framework to examine the performance of a chemical-free farming system. [ABSTRACT FROM AUTHOR]

Purpose: Deepfakes are fabricated content created by replacing an original image or video with someone else. Deepfakes have recently become commonplace in politics, posing serious challenges to democratic integrity. The advancement of AI-enabled technology and machine learning has made creating synthetic videos relatively easy. This study explores the role of political brand hate and individual moral consciousness in influencing electorates' intention to share political deepfake content. Design/methodology/approach: The study creates and uses a fictional deepfake video to test the proposed model. Data are collected from N = 310 respondents in India and tested using partial least square–structural equation modelling (PLS-SEM) with SmartPLS v3. Findings: The findings support that ideological incompatibility with the political party leads to political brand hate, positively affecting the electorates' intention to share political deepfake videos. This effect is partially mediated by users' reduced intention to verify political deepfake videos. In addition, it is observed that individual moral consciousness positively moderates the effect of political brand hate on the intention to share political deepfake videos. Intention to share political deepfake videos thus becomes a motive to seek revenge on the hated party, an expression of an individual's ideological hate and a means to preserve one's moral self-concept and strengthen their ideologies and moral beliefs. Originality/value: The study expands the growing discussion about disseminating political deepfake videos using the theoretical lens of the negative consumer-brand relationship. It validates the effect of political brand hate on irrational behavior that is intended to cause harm to the hated party. Further, it provides a novel perspective that individual moral consciousness may fuel the haters' desire to engage in anti-branding behavior. Political ideological incompatibility reflects ethical reasons for brand hate. Therefore, hate among individuals with high moral consciousness serves to preserve their moral self. [ABSTRACT FROM AUTHOR]

Purpose: The impact of COVID-19 has caused a recession in economies all over the world. In this context, the current study aims to analyze the prevailing economic scenario using a machine learning approach and suggest sustainable measures to recover the global economy taking the case of Make in India (MII) initiative of developing the economy as a base for the study. Design/methodology/approach: A well-known topic modeling technique – Latent Dirichlet allocation (LDA) algorithm has been employed to extract useful information characterizing the existing state of selected sectors under the MII initiative alongside catalytic policies that have been implemented for the same. The textual data acts as the base of the study upon which suggestions are provided. Findings: The findings obtained suggest that digital transformation will play a key role in concerned sectors to optimize the performance of manufacturing organizations. Additionally, inter-relationship between Key Performance Indicators for the economy's revival is crucial for effective utilization of foreign direct investment resources. Practical implications: The novel efforts to utilize MII initiative as a case present crucial information which can be used by policy makers and various other stakeholders across the globe to enhance decision-making and draft legislation across different sectors to empower the economy. Originality/value: The study presents a novel approach to utilize the MII initiative by identifying important measures for crucial sectors and associated policies that have been presented by employing a text mining approach which in itself makes it unique in its contribution to research literature. [ABSTRACT FROM AUTHOR]

Purpose: This article aims to model the challenges of implementing artificial intelligence and machine earning (AI-ML) for moderating the impacts of COVID-19, considering the agricultural supply chain (ASC) in the Indian context. Design/methodology/approach: 20 critical challenges were modeled based on a comprehensive literature review and consultation with experts. The hybrid approach of "Delphi interpretive structural modeling (ISM)-Fuzzy Matrice d' Impacts Croises Multiplication Applique'e à un Classement (MICMAC) − analytical network process (ANP)" was used. Findings: The study's outcome indicates that "lack of central and state regulations and rules" and "lack of data security and privacy" are the crucial challenges of AI-ML implementation in the ASC. Furthermore, AI-ML in the ASC is a powerful enabler of accurate prediction to minimize uncertainties. Research limitations/implications: This study will help stakeholders, policymakers, government and service providers understand and formulate appropriate strategies to enhance AI-ML implementation in ASCs. Also, it provides valuable insights into the COVID-19 impacts from an ASC perspective. Besides, as the study was conducted in India, decision-makers and practitioners from other geographies and economies must extrapolate the results with due care. Originality/value: This study is one of the first that investigates the potential of AI-ML in the ASC during COVID-19 by employing a hybrid approach using Delphi-ISM-Fuzzy-MICMAC-ANP. [ABSTRACT FROM AUTHOR]

Purpose: This study attempts to identify fundamental determinants of bond ratings for non-financial and financial firms. Further the study aims to develop a parsimonious bond rating model and compare its efficacy across statistical and range of machine learning methods in the Indian context. The study is motivated by the insufficiency of prior work in the Indian context. Design/methodology/approach: The authors identify the critical determinants of non-financial and financial firms using multinomial logistic regression. Various machine learning and statistical methods are employed to identify the optimal bond rating prediction model. The data cover 8,346 bond issues from 2009 to 2019. Findings: The authors find that industry concentration, sales, operating leverage, operating efficiency, profitability, solvency, strategic ownership, age, firm size and firm value play an important role in rating non-financial firms. Operating efficiency, profitability, strategic ownership and size are also relevant for financial firms besides additional determinants related to the capital adequacy, asset quality, management efficiency, earnings quality and liquidity (CAMEL) approach. The authors find that random forest outperforms logit and other machine learning methods with an accuracy rate of 92 and 91% for non-financial and financial firms. Practical implications: The study identifies important determinants of bond ratings for both non-financial and financial firms. The study interalia finds that the random forest technique is the most appropriate method for bond ratings predictions in India. Social implications: Better bond ratings may mitigate corporate defaults. Originality/value: Unlike prior literature, the study identifies determinants of bond ratings for both non-financial and financial firms. The study also experiments with modern machine learning techniques besides the traditional statistical approach for model building in case of relatively under researched market. [ABSTRACT FROM AUTHOR]

Behavioral finance literature has long claimed that internet stock message boards can move markets. In this chapter, the authors study more than 2,000 internet board messages posted across finance message boards in India (Chittorgarh, etc.) for 110 companies that went for initial public offering (IPO) in the last one year. This study has multi-fold objectives. First, the authors try to identify the factors which lead to a discussion on an IPO stock in the message board. Second, the authors identify the factors which differentiate a widely discussed stock from the less discussed one. Next, the authors apply advanced machine learning technique to identify the topics which are discussed in the message board through automatic topic modeling. The methodology used includes a logistic regression model for identifying firm characteristics which leads to a probability of getting stakeholders' attention and hence more discussion. The authors also use advanced topic modeling techniques to identify topics of discussion on the message boards through machine learning. The authors find that larger sized firms, younger firms, firms with low leverage, and nonmanufacturing firms get discussed more and the topics of discussion relate to their financial statements, trading strategies, stock behavior, and performance. [ABSTRACT FROM AUTHOR]