Stock Price Prediction Using Mamba

Abstract

The prices in the stock market constantly fluctuate due to the influence of internal and external dynamics. For investors, predicting these movements can provide a significant advantage. Accurately forecasting stock prices is crucial for both reducing investment risks and increasing returns, while preventing financial losses. However, the volatile and complex nature of financial markets makes this process challenging. Recently, models like Mamba, based on state space models, have delivered effective results in sequence modelling. In this study, the goal was to predict stock closing prices using the Mamba model. The model's performance was evaluated on the prices of six companies listed on the Nasdaq. Mamba demonstrated better performance with lower error rates compared to our baseline models, MLP and LSTM. These results may help investors reduce risks and make more informed decisions. © 2024 IEEE.