Robust Multi-Objective Optimization Model for Reserve and Credit Fund Allocation in Banking Under Conditional Value-at-Risk Constraints

In the realm of financial management, optimizing the allocation of funds in banking companies is vital to their operational efficiency. Banks manage their funds by allocating them into reserve and credit funds as the main activities of banking. Optimizing these allocations ensures that all assets are effectively utilized. However, real-life optimization problems often involve uncertainty, making deterministic data assumptions insufficient. Robust Optimization is a methodology that addresses these uncertainties by incorporating computational tools to solve optimization problems with uncertain data. The uncertainty approach used in robust optimization is polyhedral sets. In the context of banking, uncertainties influencing the allocation of reserve and credit funds include financial risks and returns. These risks can be quantified using Conditional Value-at-Risk (CVaR), a suitable measure for banking fund allocation due to its ability to accommodate varying risk characteristics under different business conditions. This study focuses on developing an optimization model for reserve and credit fund allocation in banking companies using a Multi-objective Robust CVaR approach with lexicographic, informed by business risk data and credit instruments. The resulting optimization model yields optimal allocations for reserve and credit funds, ensuring efficient asset utilization to support banking operations. This approach offers new perspectives for banks to achieve fund allocations that are not only regulatory compliant but also optimal. The implications of such optimal allocations include mitigating risks associated with reserve fund imbalances and enhancing profitability through optimal credit returns.