My objective in this project is to forecast the gold price (per gram) for the next 6 months using historical data. Given the randomness in gold prices, this task will be a significant challenge
I studied monthly records of gold prices in Indian rupees from 1979 to 2022, employed a range of statistical models including Moving Average (MA), Autoregressive (AR), Autoregressive Moving Average (ARMA), and Seasonal Autoregressive Integrated Moving Average (SARIMA) to analyze trends and seasonal patterns. To create a predictive model, I used machine learning algorithm such as linear regression. To further enhance accuracy, deep learning models such as RNN and LSTM were employed. Based on the Root Mean Square Error (RMSE) metric, the RNN model emerged as a best choice, enabling us to forecast gold prices for the next six months with confidence interval.