Analyzing of financial market and estimate future prices: A case study of the google stock

The exceptionally dynamic nature of financial markets presents market analysts, investors, and researchers from a wide range of industries with a multitude of opportunities. Maximizing profits is the primary objective of investments in the financial markets. An individual engages in the buying and selling of securities on the financial marketplace known as the stock market. Because of this, the complex nature of the endeavor, which demands a thorough understanding of a multitude of interconnected elements, forecasting stock prices for publicly traded companies operating in the securities sector can be challenging. A multitude of determinants influence the stock market, encompassing political, economic, and societal aspects. Advancements in technology and artificial intelligence offer investors a more dependable alternative. This research provides a novel model that combines the CatBoost approach with the Marine Predators Algorithm strategy to tackle many difficulties efficiently. The hybrid model outperformed the other models in this research for both efficiency and performance. The investigation examined the predictive power of a proposed framework for predicting stock prices using Google stock data from January 1, 2015, to June 29, 2023. The Friedman Chi-square, P-value, and cross-validation were used to evaluate the proposed method. Additionally, the performance of the proposed model for the additional four markets, DAX, FTSE, HSI, and SSE, was evaluated and it achieved <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mrow> <mml:msup> <mml:mtext>R</mml:mtext> <mml:mtext>2</mml:mtext> </mml:msup> </mml:mrow> </mml:math> values of above 0.99 for all these markets. The findings demonstrate that the proposed model is a dependable as well as beneficial approach for generating time series data on stock prices.