Introducing a Novel Method for Determining the Future Price of the Financial Markets: A Case Study of the Hang Seng Index

The stock market is highly complex, with numerous unpredictable factors influencing stock prices. The relationship between supply and demand, alongside external events, makes it difficult to forecast future market behavior with high accuracy. While stock market investing offers long-term profit potential, predicting future trends remains a challenge in part because of the dynamic and volatility character of financial markets. This study seeks to address these challenges by developing an accurate hybrid forecasting model that integrates optimization algorithms with the CatBoost machine learning model. The goal of financial market investments is to maximize earnings, which is contingent upon several changing circumstances. However, it is difficult to predict the market's future behavior due to its complexity and the large range of events that affect it. The objective of this study is to develop a precise hybrid stock price forecasting model combining optimizers and CatBoost. By utilizing the Hang Seng Index market data from 2015 to 2023, this study aims to produce accurate forecasting. Grey Wolf Optimization, Slime Mold Algorithm, and Genetic Algorithm are the optimization techniques included in this study. Of all these optimization methods, Grey Wolf Optimization in combination with CatBoost has been shown to yield the best outcomes. The value of the Correction Coefficient for the proposed model was 0.9949 which shows the highest efficiency in comparison to other models. As a result, the suggested model can be effective for investors in the financial market.