Algorithmic Trading and AI-Enhanced Portfolio Management for Revenue Optimization in Commercial Banking
Аннотация
Algorithmic trading frameworks (including AI-driven agents) are increasingly used to support portfolio management decisions, yet few have been calibrated specifically for the revenue optimization needs of commercial banking institutions. The proposed hybrid model is shown to be effective with the integration of algorithmic trading tools because it incorporates the TOPSIS–survival modeling approach and enables more granular insights for decision-making in risk-sensitive portfolios. The aim of this study was to improve revenue making in the context of dynamic financial markets. Survival analysis and ranking algorithms were applied to compare portfolio trajectories to identify risk factors, reveal ways that algorithmic models could best support asset allocation for both long-term growth and short-term liquidity, and enhance precision and timing accuracy for a competitive edge. Through a focus on data-driven reasoning, we show how reading survival probabilities can inform AI-based decisions about asset rebalancing and add to strategic understanding of volatility in banking portfolios. These findings, coupled with multi-period optimization and ranking analysis, resulted in the development of AIPORT – a decision-support platform to improve profitability and risk forecasting. The results showed that revenue outcomes and portfolio durability increased when AI-enhanced strategies were aligned with market indicators and their temporal behaviors, and when managers adjusted their investment weights for volatility clustering at different horizons after model evaluation. Data–model synergies can accelerate the development of customized trading algorithms specifically for banks with diversified portfolios.