Estimating Economic Insights: A Machine Learning Method for Estimating the Shanghai Stock Exchange

The stock market is an environment where individuals participate in the purchase and sale of shares in publicly traded companies. It serves as a gauge of a country's economic well-being and the overall business environment. Stock prices are governed by the balance between supply and demand. Engaging in stock market investments may be uncertain, but it has the possibility of providing substantial profits in the long run. Investing in the financial market seeks to maximize earnings, which depends on several fluctuating conditions. Nonetheless, it is challenging to anticipate the market's future actions because of its intricacy and the wide array of events that impact it. This work aims to create an accurate hybrid model for predicting stock prices which includes Adaptive Boosting, Slime mould algorithm, and Empirical mode decomposition (EMD) to forecast the stock market values. EMD is one of the methods for the decomposition of nonstationary and nonlinear time series data into simpler components. The optimization techniques used are Slime mould algorithm (SMA) and Grey Wolf Optimization (GWO) because of their efficiency in fine-tuning model parameters. These will further enhance the capability of the model to process the complex data of the stock market for high-accuracy prediction. This study seeks to create precise predictions by using the market historical data including open, high, low, trading volume, and close prices of the Shanghai Stock Exchange Index from 2015 to 2023. To reduce the complexity of the dataset, Empirical mode decomposition is used. To reduce the complexity of the dataset, Empirical mode decomposition is used. Then, SMA showed a better result. The EMD-SMA-AdaBoost model indicates the highest efficiency of the other models giving the R2 value of 0.9932.