R.Gowthami,K.Lakshmi 02 05(1) This study undertakes an advanced and comprehensive financial statement analysis of Bank of Baroda one of Indias leading public sector banks by strategically integrating traditional financial ratio analysis with cuttingedge Machine Learning ML and Deep Learning DL methodologies Acknowledging the inherent limitations of conventional static analysis in capturing the complex dynamics of the banking sector the research will systematically collect and scrutinize Bank of Barodas audited financial statements over a significant 510 year historical period eg FY2015FY2024 This extensive dataset will first be used to compute a nuanced array of bankspecific financial ratios spanning critical dimensions such as liquidity eg Advances to Deposits Ratio profitability eg Net Interest Margin Return on Assets solvencycapital adequacy eg Capital Adequacy Ratio and asset quality eg Gross NonPerforming Assets ratio Following a traditional trend analysis and benchmark comparison against peer banks in the Indian landscape the study will delve into advanced analytics ML models specifically powerful ensemble techniques like Random Forest and XGBoost will be meticulously applied to identify the most influential ratios and underlying financial factors that significantly impact the banks core profitability metrics and asset quality thereby uncovering previously hidden or less obvious relationships and drivers Furthermore to address the critical need for forwardlooking insights Deep Learning models particularly Long ShortTerm Memory LSTM networks will be developed and deployed for forecasting crucial future financial metrics These LSTMs are uniquely capable of capturing intricate temporal dependencies seasonal patterns eeg quarteronquarter variations in credit growth or deposit mobilization and market volatilities that profoundly affect banking operations The performance of these AIdriven forecasting models will be rigorously evaluated against traditional linear timeseries models using metrics such as Mean Squared Error MSE and prediction accuracy with the expectation of demonstrating superior predictive power Ultimately this research aims to provide Bank of Barodas stakeholders including management regulators and investors with more robust dynamic and datadriven insights enhancing strategic decisionmaking capabilities optimizing risk management frameworks and fostering greater financial stability in a complex and evolving banking environment Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026