Rakshith Bhandary

Dr. Rakshith Bhandary

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
RBRakshith Bhandary
Rakshith Bhandary
BGBidyut Kumar Ghosh
Bidyut Kumar Ghosh
This article compares the predictive capabilities of six models, namely, linear discriminant analysis (LDA), logistic regression (LR), support vector machine (SVM), XGBoost, random forest (RF), and deep neural network (DNN), to predict the default behavior of credit card holders in Taiwan using data from the UCI machine learning database. The Python programming language was used for data analysis. Statistical methods were compared with machine learning algorithms using the confusion matrix measured in metric terms of prediction accuracy, sensitivity, specificity, precision, G-mean, F1 score, ROC, and AUC. The dataset contained 30,000 credit card users’ information, with 6636 default observations and 23,364 nondefault cases. The study results found that modern machine learning methods outperformed traditional statistical methods in terms of predictive performance measured by the F1 score, G-mean, and AUC. Traditional methods like logistic regression were marginally better than linear discriminant analysis and support vector machines in terms of the predictive performance measured by the area under the receiver operating characteristic curve. In the modern machine learning methods, deep neural network was better in the predictive performance metrics when compared with XGBoost and random forest methods.

5 October 2023 in Journal of Financial Services Marketing
Verified
Journal Article
Open access
PDF file
RBRakshith Bhandary
Rakshith Bhandary
SSSandeep S Shenoy
Sandeep S Shenoy
ASAnkitha Shetty
Ankitha Shetty
ASAdithya D. Shetty
Adithya D. Shetty
Education is a significant contributor to human capital. Financial assistance for education through institutional loan serves as the key element for human development, and loan repayment without default makes the education loan product self-sustainable. The systematic review aims to study the various articles related to education loan repayment (ELR) using bibliometric analysis approach and R studio software with the help of biblioshiny package. The study analyses 812 articles published in the Scopus database between 1990 and 2022. The review identifies most relevant authors, most cited articles, publication trends, keywords and themes, and trending topics. The review finds that research in the domain of ELR is at an increasing trend with a growth rate of 7.2% and, in the year 2022, the highest number of scientific publications, that is, 72 articles, was published. The review exhibits that existing research in the field has mainly focused on themes such as repayment burden, financial literacy, financial education, student debt, income, mental health, and loan defaults. The study concludes that highly cited work in educational loan repayment is in the field of medicine, highlighting salary as the key factor for educational loan repayment, and loan repayment is incentivized by the federal government to serve the designated underserved areas through service option loan repayment programs. Methods on designing and marketing new approaches to loan repayment can be researched in future with relation to human resource recruitment and retention by the employers.

Verified
Journal Article
Open access
PDF file
DFDaniel Frank
Daniel Frank
RBRakshith Bhandary
Rakshith Bhandary
SPSudhir K. Prabhu
Sudhir K. Prabhu
Education is considered an investment in human capital that is gained at the cost of knowledge acquisition. This cost is borne by the beneficiary along with subsidy provided by the government, if any, that is mainly collected through tax revenues. This article aims to systematically review the utility derived and the burden experienced with educational debt borrowers across the globe as per the three types of educational loan schemes present across the globe. This study follows the PRISMA guidelines for review selection, and 47 articles published between 1994 and 2024 were included for the final review. The study results reveal that education improves the quality of life; an educational debt servicing to income ratio above 8% is considered as a financial burden. Also, the results reveal that material benefits are high after education along with an increase in the psychological burden because of repayment concerns. This study highlights the need to move towards designing a flexible repayment system in the education loan scheme based on the income contingent schemes adopted in many countries. Income contingent schemes reduce the repayment burden of the borrowers but the return to the lender is limited to the income of the borrower, and mortgage-based schemes are associated with high repayment burden. Therefore, a dynamic scheme will fix the problems associated with the repayment burden by creating a dynamic link between the benefits received and the contributions made by the borrower.

1 July 2018 in Indian Journal of Marketing
Verified
Journal Article
Closed access
BSBhavna Shetty
Bhavna Shetty
RBRakshith Bhandary
Rakshith Bhandary
SCSachin R. Chandra
Sachin R. Chandra
ASAdithya D. Shetty
Adithya D. Shetty
Antecedents to Customer Loyalty in the Restaurant Industry : A Millennial Perspective

9 September 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
DPDuddela Sai Prashanth
Duddela Sai Prashanth
RBRakshith Bhandary
Rakshith Bhandary
BRBharath Rai
Bharath Rai
SHShivaraj
Shivaraj
VLVaishnavi Laxmi
Vaishnavi Laxmi
VJVignesh D. Jogi
Vignesh D. Jogi
Music is an expression of emotion and a universal language that connects people across various cultures. From timeless classical pieces to modern electronic beats, artificial intelligence is capable of composing, arranging, and even crafting refined musical arrangements in a wide variety of styles. This study, trains and develops an automated model to create melodies, on the monophonic genre specific datasets that serve as inputs to the Melody Generative System (MGS) to generate and compose melody automatically. To accomplish this, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) network and Generative Adversarial Network (GAN) was used. To train the model, we used musical datasets, in Kern and MIDI formats primarily featuring solo piano compositions. Here, the Kern dataset uses specific text based notations to represent musical elements, whereas MIDI is a format containing information about musical performance data like notes and duration. This article also compares the results obtained from three different architectures using different activation functions, distinctly tanh and softmax. The study found that, tanh activation function led to higher accuracy and lower loss compared to softmax function in generating melodies. The comparative analysis of the 3 networks prove that, RNN-LSTM has the best accuracy of 98.39% for 80 − 20 train-test-split. Whereas, the performance of GAN network fell short compared to Simple RNN and RNN-LSTM when trained with both Kern and MIDI datasets. This study showcases the capabilities of different melody generation algorithms for generating monophonic melodies, and also demonstrates how deep learning can effectively recognize and replicate musical patterns.

31 January 2025
Verified
Preprint
Open access
PDF file
RBRakshith Bhandary
Rakshith Bhandary
This paper examines the input variables of loan repayment behavior on digital lending platforms. The idea is interesting, and the method employed is appropriate for the large corpus of literature in the field. Nevertheless, the paper could be improve...