| Summary: | The stock market's ever-evolving landscape is characterized by its capricious nature, rendering the task of stock price prediction highly intricate. The intertwining variables such as global political scenarios, company performance, and public sentiment contribute to the volatility of stock prices, making predictions even more sophisticated. However, the rapidly advancing realm of machine learning and deep learning like Gated Recurrent Unit (GRU) has begun to hold significant promise in tackling these challenges.
This project aims to use GRU network to predict gold price using its historic value and evaluating its accuracy with other traditional neural networks.
|
|---|