Downloads: 17
India | Computer Methods in Applied Mechanics and Engineering | Volume 14 Issue 8, August 2025 | Pages: 72 - 93
Financial Predictions of Gold Prices using Time Series Analysis
Abstract: Gold has long been recognized as a safe-haven asset and a hedge against inflation, especially during times of economic uncertainty. This study aims to forecast gold prices using time series analysis, drawing on historical data from 2019 to 2024. Multiple forecasting models- ARIMA, SARIMA, Exponential Smoothing, and Prophet- were evaluated to determine the most reliable method. Given the presence of significant market volatility and outliers in the dataset, the Prophet model was selected for its robustness to irregularities and ability to model complex seasonality. The data underwent preprocessing. The final model forecasted daily gold prices for 2025, revealing a projected upward trend. This aligns with current macroeconomic indicators such as persistent inflation, geopolitical instability, and ongoing global conflicts- factors historically known to increase demand for gold. The study concludes that gold prices are likely to rise in 2025, reinforcing gold?s role as a strategic investment asset. These insights can support better investment decision-making in uncertain economic climates.
Keywords: Gold Prices, Time Series Forecasting, Prophet Model, ARIMA, SARIMA Exponential Smoothing, Train-Test Split, Data Preprocessing, Forecast Accuracy, Performance Metrics (MAE, RMSE, MAPE), Trends, Seasonality, Stationarity
How to Cite?: Vedika Bansal, "Financial Predictions of Gold Prices using Time Series Analysis", Volume 14 Issue 8, August 2025, International Journal of Science and Research (IJSR), Pages: 72-93, https://www.ijsr.net/getabstract.php?paperid=SR25723213956, DOI: https://dx.doi.org/10.21275/SR25723213956
Received Comments