AI-Driven Risk Prediction in Investment Portfolios
Main Article Content
Abstract
Speculation portfolios are intrinsically presented to different dangers that can sabotage monetary steadiness and returns. This review investigates a man-made consciousness (computer-based intelligence)- driven structure for powerful gamble expectation in speculation portfolios, utilizing progressed information preprocessing, highlight choice, and grouping strategies. The preprocessing stage utilizes exception discovery procedures to guarantee information quality and dispense with irregularities that could slant expectations. For highlight determination, Recursive Element End (RFE) is used to recognize the most powerful monetary pointers, improving model effectiveness and interpretability. Irregular Woodland, a hearty characterization calculation, is applied to foresee risk classifications with high exactness and strength against overfitting. The proposed approach is approved on genuine world monetary datasets, exhibiting its adequacy in anticipating portfolio risk while keeping up with straightforwardness and versatility. This examination highlights the capability of coordinating man-made intelligence procedures into monetary gamble the executives, offering an information driven answer for upgrade venture systems and improve dynamic under questionable economic situations.