Predicting Chinese Gold Prices: A Comparative Study of LSTM and Random Forest Models

The rapid recovery of the domestic economy in China after the pandemic is now making the gold market more popular. Therefore, the technical methods to predict the gold price are required for the current market situation. This paper presents a comparative analysis of Long Short-Term Memory (LSTM) and Random Forest (RF) models for forecasting gold prices in China from 2013 to 2023. The study aims to evaluate the predictive accuracy of these two machine learning models and determine which one is more suitable for forecasting gold prices. The LSTM model, with its ability to capture temporal dependencies, and the RF model, known for its robustness in handling non-linear relationships, are both trained and tested on the same dataset. The results of this study can provide valuable insights for investors and policymakers in the financial sector. The conclusion indicates that the LSTM model shows better performance on the prediction, which means this model is more likely to be widely used in practical operations. The findings are expected to shed light on the most effective machine learning approaches for predicting gold prices, thereby enhancing the predictive power and reliability of financial models in the context of Chinese gold markets.