English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The main motivation of this study is to forecast the performance of Indian banks using multiple regression analysis and artificial neural network and to compare these two methods for the accuracy. To achieve this goal, financial data spread over 10 years from 2010 to 2019 was collected from 19 Indian public sector banks. The data consists of 17 financial ratios collected from financial statements and other publications of the sample organizations. Capital Adequacy Ratio (CRAR) has been chosen as dependent variable for measuring and predicting the financial strength of banks. Identification of significant ratios that are determinants of CRAR are identified by using regression technique then these identified ratios are used as input for a developing a neural network model. The findings of multi-linear regression analysis identified 7 financial ratios that have a positive relationship between with dependent variable (CRAR). These 7 dependent variables were used to predict the financial strength (CRAR) of the Banks. Then a feed forward back propagation neural network was developed with these 7 dependent variables to predict the CRAR. Finally, the performances of these two methods were measured by using the Mean Square Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Percent Error (MAPE). The results indicate that ANN model scores an improvement of 55.67% in MSE over regression model. In RMSE which re-scales the errors in order to keep the errors’ dimension as the predicted value, ANN model scores an improvement of 33.425% over regression model. It also indicates that ANN model scores an improvement of 99.32% over regression model in MAPE which measures the magnitude of absolute errors in relative terms. Results show that ANN model outperforms the regression model and is superior technique of forecasting CRAR of Indian Banks. Key-Words: Machine Learning (ML), Regression, Artificial Neural Networks (ANN), Capital Adequacy Ratio (CRAR), Financial Ratios, Financial Strength, Bankruptcy Received: April 18, 2019. Revised: May 30, 2020. Accepted: June 8, 2020. Published: June 10, 2020

wseas transactions on business and economics

A Comparative Study of Multiple Regression Analysis and Back Propagation Neural Network Approaches on Predicting Financial Strength of Banks: An Indian Perspective