AI-Driven Financial performance evalution of indian banks using explainable machine learning and hybrid multi-criteria decision-making

Abstract

Abstract The rapid digital transformation of the Indian banking sector has significantly increased the availability of financial and operational data, creating opportunities for artificial intelligence (AI)-based decision-making. Conventional financial performance evaluation methods primarily rely on ratio analysis and statistical techniques, which often fail to capture complex nonlinear relationships among financial indicators and provide limited interpretability for stakeholders. This study proposes an integrated framework combining Explainable Machine Learning (XML) and Hybrid Multi-Criteria Decision-Making (MCDM) techniques to evaluate the financial performance of Indian banks. The proposed framework employs machine learning algorithms to predict overall financial performance while incorporating Explainable AI (XAI) techniques, including SHAP (SHapley Additive exPlanations), to interpret feature importance and improve transparency. Furthermore, the study integrates the Analytical Hierarchy Process (AHP) for determining criteria weights and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for ranking banks according to multiple financial indicators. Financial variables such as Return on Assets (ROA), Return on Equity (ROE), Capital Adequacy Ratio (CAR), Net Interest Margin (NIM), Gross Non-Performing Assets (GNPA), Cost-to-Income Ratio (CIR), Liquidity Ratio, and Credit-Deposit Ratio (CDR) are considered in the proposed evaluation framework. The integrated AI–MCDM approach provides a transparent, data-driven, and explainable decision-support system that enhances managerial decision-making, regulatory monitoring, and investment analysis. The findings are expected to demonstrate that combining explainable machine learning with hybrid MCDM produces more reliable and interpretable financial performance assessments than conventional approaches. The proposed framework contributes to the growing literature on AI-enabled financial analytics and offers practical implications for bank managers, investors, policymakers, and financial regulators in India's evolving digital banking ecosystem. Keywords: Explainable Artificial Intelligence (XAI), Financial Performance Evaluation, Indian Banks, Hybrid MCDM, Machine Learning