Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

An integrated framework for predicting the best financial performance of banks: evidence from Egypt

An integrated framework for predicting the best financial performance of banks: evidence from Egypt This study aims to develop and test a framework for integration between data envelopment analysis (DEA) and artificial neural networks (ANN) to predict the best financial performance concerning return on assets and return on equity for banks listed on the Egyptian Exchange, to help managers generate what-if scenarios? For performance improvement and benchmarking.Design/methodology/approachThe study empirically tested the three-stage DEA-ANN framework. First, DEA was used as a preprocessor of the banks’ efficiency scores. Second, a back-propagation neural network as a multi-layer perceptron-ANN’s model was designed using expected data sets from DEA to learn optimal performance patterns. Third, the superior performance of banks was forecasted.FindingsThe results indicated that banks are not operating under their most productive operations, and there is room for potential improvements to reach outperformance. Moreover, the neural networks’ empirical test results showed high correlations between the actual and expected values, with low prediction errors in both the test and prediction phases.Practical implicationsBased on best performance prediction, banks can generate alternative scenarios for future performance improvement and enabling managers to develop effective strategies for performance control under uncertainty and limited data. Besides, supporting the decision-making process and proactive management of performance.Originality/valueDespite the growing research stream supporting DEA-ANN integration applications, these are still limited and scarce, especially in the Middle East and North Africa region. Therefore, the study trying to fill this gap to help bank managers predict the best financial performance. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Modelling in Management Emerald Publishing

An integrated framework for predicting the best financial performance of banks: evidence from Egypt

Loading next page...
 
/lp/emerald-publishing/an-integrated-framework-for-predicting-the-best-financial-performance-yxYwUIzc9X
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1746-5664
eISSN
1746-5664
DOI
10.1108/jm2-02-2021-0040
Publisher site
See Article on Publisher Site

Abstract

This study aims to develop and test a framework for integration between data envelopment analysis (DEA) and artificial neural networks (ANN) to predict the best financial performance concerning return on assets and return on equity for banks listed on the Egyptian Exchange, to help managers generate what-if scenarios? For performance improvement and benchmarking.Design/methodology/approachThe study empirically tested the three-stage DEA-ANN framework. First, DEA was used as a preprocessor of the banks’ efficiency scores. Second, a back-propagation neural network as a multi-layer perceptron-ANN’s model was designed using expected data sets from DEA to learn optimal performance patterns. Third, the superior performance of banks was forecasted.FindingsThe results indicated that banks are not operating under their most productive operations, and there is room for potential improvements to reach outperformance. Moreover, the neural networks’ empirical test results showed high correlations between the actual and expected values, with low prediction errors in both the test and prediction phases.Practical implicationsBased on best performance prediction, banks can generate alternative scenarios for future performance improvement and enabling managers to develop effective strategies for performance control under uncertainty and limited data. Besides, supporting the decision-making process and proactive management of performance.Originality/valueDespite the growing research stream supporting DEA-ANN integration applications, these are still limited and scarce, especially in the Middle East and North Africa region. Therefore, the study trying to fill this gap to help bank managers predict the best financial performance.

Journal

Journal of Modelling in ManagementEmerald Publishing

Published: Aug 22, 2022

Keywords: Financial performance; Data envelopment analysis (DEA); Artificial neural networks (ANN); Banks; Egypt; Benchmarking; Linear programming; Neural networks

References