Improved Whale Optimization Algorithm for supply chain financial risk assessment of cloud warehouse platform

This study provides an in-depth analysis of a new financial model for cloud warehouses and evaluates the associated credit risk within the context of supply chain financing, focusing on the intelligent transformation in this field. Concurrently, an optimization problem was derived from the evaluation issue, with the whale optimization algorithm (WOA) used to identify a reasonable default point and distance. To simplify the identification of these points, we enhanced the traditional WOA, resulting in an improved version, the IWOA, which demonstrated very good optimization performance. The IWOA's optimization capabilities were applied to determine the optimal ratio of short- and long-term debt coefficients, identifying the default point in the Kealhofer, McQuown, and Vasicek (KMV) credit monitoring model, replacing fixed values and yielding more precise results. Furthermore, this study introduces a novel analytical approach to credit risk measurement, advancing the development of related theories and methods. Accurate analysis of financial stability and risk is crucial in industrial sectors, including engineering and manufacturing. The simulation using specific data revealed that the IWOA-KMV model exhibited better and faster optimization capabilities, with greater discrimination ability compared to the KMV model. Overall, this study examines the risk factors in the cloud warehouse financing model, offers an improved version of the WOA, introduces a modified IWOA-KMV model to create a scientific, practical credit risk assessment framework, and provides guidance for risk control in cloud warehouse financing, a novel financing service.