Dr.P.Janaki Ramulu,K.Archana,K.Sravanthi 02 05(1) Investment banks generate revenue through a range of complex and dynamic fee structures including advisory fees underwriting spreads success fees and retainers Traditionally fee determination and analysis have relied on historical averages industry benchmarks and linear models often missing deeper relationships hidden within vast deal datasets This study begins with a comprehensive analysis of investment bank fee structures examining how fees vary by deal type size sector region and economic contextBy extending the research to include Machine Learning ML and Deep Learning DL techniques we aim to reveal nonlinear patterns and identify the key drivers of fee variability that traditional methods overlook ML models such as Random Forest and XGBoost are applied to predict fee percentages based on deal characteristics client type and market conditions providing clearer insight into pricing strategies In parallel LSTM networks are used to forecast timeseries trends in aggregate fee income capturing seasonality and market cycles in a way that linear forecasting cannotOur integrated approach demonstrates that AI models not only enhance forecasting accuracy but also uncover complex interactions between variables like market volatility deal complexity and client segment The findings offer actionable insights for banks to design competitive yet profitable fee strategies and better align resources with market demand Overall this study illustrates the power of combining traditional financial analysis with modern AI tools to transform decisionmaking and strategy in investment banking Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026