Stock Price Prediction: A Comparative Study of Random Forest and LSTM Models

This is the authors' abstract. We don't add key points for this paper.

With the escalating globalization and intricacies of financial markets, accurate stock price forecasting has become paramount for investors, analysts, and researchers. This study compares the effectiveness of Random Forest and Long Short-Term Memory (LSTM) in predicting Tesla stock prices. Utilizing historical data refined for sequential analysis, both models were trained and tested. Evaluation metrics such as Mean Square Error (MSE) and accuracy were used to assess predictive prowess. Results indicate that LSTM exhibits superior accuracy in forecasting Tesla stock prices, owing to its proficiency in managing long-term dependencies and nonlinear relationships inherent in stock price time series data. Conversely, Random Forest's performance was relatively limited. On the other hand, the random forest model has the advantage of running time much lower than LSTM. This research underscores the significance of model selection tailored to the unique characteristics of financial data and opens avenues for future explorations in optimizing predictive models and translating insights into practical stock trading strategies.