Prediction of Financial Time-series Data Using ARIMA Model and Machine Learning Algorithm

Stock price prediction is a crucial area in finance, directly influencing investment decisions, market strategies, and the broader economic landscape. Using the stock price of BHP Group Ltd. as a case study, we compare the performance of the ARIMA model and the LSTM network for stock price prediction. For the ARIMA model, we utilize log-return data to predict stock prices. Our results indicate that while the ARIMA model performs reasonably well for short-term predictions, its accuracy diminishes for long-term predictions due to its inherently linear nature. A notable advantage of the ARIMA model is its ability to deliver results without requiring extensive data for training. Conversely, the LSTM algorithm demonstrates higher accuracy, particularly for long-term predictions, though it requires a larger dataset to train effectively.