Optimization of Long Short Term Memory Model for Gold Price Prediction Using Adaptive Moment Estimation

The era of globalization and rapidly evolving economic dynamics place the financial sector at the center of attention for market participants and investors. Financial instruments such as gold play a crucial role as hedging tools and portfolio diversification, yet face significant challenges due to complex and unpredictable price fluctuations. Artificial intelligence technology, particularly Long Short Term Memory (LSTM) models and Adaptive Moment Estimation (ADAM), offers relevant solutions for predicting financial asset prices with strong temporal fluctuations, such as gold prices. This research aims to optimize the LSTM model using the ADAM technique to enhance the accuracy of gold price predictions. The research findings indicate that the LSTM model optimized with ADAM can provide highly accurate gold price predictions with low error rates. The LSTM model used has 3 layers with 128, 64, and 32 units, and uses 100 epochs in the model training process. At the 100th epoch, the final loss obtained was 0,000336. Model evaluation results showed a MAPE of around 0,0108 or 1,08% an accuracy rate of about 98,92%, and a low loss value of 0,00025.