Search

The banking sector in India plays a crucial role in economic growth. A bank provides an opportunity for investments to encourage economic growth and the potential to yield higher returns. In this study, we develop a bankruptcy prediction model by using machine learning (ML) techniques, namely logistic regression, random forest, and AdaBoost, and compare these models with those developed using deep learning (DL) techniques, namely the artificial neural network (ANN). ANN results in the highest accuracy and the most favourable prediction model for bankruptcy. Data used in this study are collected from survived and failed private and public sector banks from India from March 2001 to March 2018. For bankruptcy prediction, we use the bank's macroeconomic and market structure-related features. The feature selection technique 'Relief algorithm' is used to select useful features for the bankruptcy prediction model. Because failed banks in comparison with survived were less in the dataset, the issue of imbalanced cases may have arisen, in which case most ML and DL techniques do not perform well. Thus, we convert the dataset into a balanced form by using the synthetic minority oversampling technique (SMOTE). The results of this study can help in performing financial analyses of banks and thus have significant implications for their stakeholders. [ABSTRACT FROM AUTHOR]

The purpose of the current research is to understand the influence of vendor cues like brand reputation. Brand familiarity and offline presence on trust and attitude of online shoppers and consequently on online purchase intention. Data was collected through a web based survey. The findings of the study reported that vendor offline cues have a strong and positive impact on the online purchase intentions of the shoppers. Further, this study also contributed by proving that the trust has a strong relationship with purchase intention as compare to attitude. [ABSTRACT FROM AUTHOR]

Biogas, the end product of anaerobic digestion of cattle dung, can successfully supplement the cooking fuels in the countryside areas of India, where the raw material needed for its production is plentifully available. Because of the lack of awareness regarding selection of a suitable model and size of biogas plant, the full potential of the biogas producing material is not harnessed, and the economic viability of biogas technology is rendered doubtful. To facilitate this decision making, the economics of family size biogas plants, i.e. with capacity from 1 to 6 m3, was studied, and three prevalent models, viz. KVIC, Janta and Deenbandu, were compared. Calculations for installation cost and annual operational cost were made for the state of Punjab, India, where the hydraulic retention time is 40 days, and current market prices were taken into account. Comparison of the economics revealed that the cost of installation and annual operational cost of each capacity were higher for the KVIC model, followed by the Janta and then the Deenbandhu model. Irrespective of the model, as the capacity of the biogas plant increases, the installation, as well as the annual operational cost increase proportionately. With increase in capacity, the payback period decreased exponentially with the exponential character being highest for the KVIC model, followed by the Janta and then the Deenbandhu model. However, on the basis of comparative economics, the Deenbandhu model was found to be the cheapest and most viable model of biogas plant. [Copyright &y& Elsevier]