Analyzing the performance of the hybrid model in relation to the Nikkei 225 index for estimation of the stock future prices
摘要
The stock market involves a variety of ownership interests, from shares of publicly traded companies to privately held assets. Trading stocks is a major part of financial markets, but the unpredictable nature of stock prices means investors need reliable forecasting tools to minimize risks and boost returns. This study tackles the shortcomings of traditional forecasting models by introducing a new hybrid approach with integration of the metaheuristic optimization models. This model blends a Decision Tree with the Aquila Optimizer to improve prediction accuracy. The research also involves thorough data preparation, using historical data from the Nikkei 225 index covering 2013 to 2022. The data was split into training and testing sets, ensuring the model was well-trained and tested on fresh data. The findings show that the proposed model outperforms older methods, making it a dependable option for predicting stock prices. Additionally, the study compared three optimization techniques Genetic Algorithm, Battle Royale Optimizer, and Aquila Optimizer and found that the proposed model provided the most accurate results with