Impact of Bitcoin Returns on U.S. Gold Using ARIMA and LSTM Models
- DOI
- 10.2991/978-94-6463-872-1_33How to use a DOI?
- Keywords
- Bitcoin; US Gold; ARIMA; LSTM; Time-Series; Deep Learning; Volatility
- Abstract
The research evaluates the relationship between Bitcoin returns and US Gold prices using both traditional and deep learning predictive models. It analyzes Bitcoin’s volatility through time-series data from 2017 to 2025 to assess its impact on US Gold prices, which have traditionally exhibited greater stability. Forecasting accuracy is examined by applying the ARIMA and LSTM to both asset classes. The LSTM model demonstrates superior performance compared to the ARIMA model, as evidenced by lower RMSE, MAE, and MAPE values, due to its ability to capture nonlinear trends and complex market dynamics. The findings suggest that Bitcoin’s price fluctuations may influence subsequent movements in gold prices, positioning Bitcoin as a potential economic indicator that challenges the traditional role of gold as a safe-haven asset. This study offers practical insights for investors, financial analysts, and policymakers, advocating for a revised portfolio strategy that incorporates Bitcoin and supports the use of advanced machine learning models in financial forecasting.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Nitendra Kumar AU - Shashwat Kapoor PY - 2025 DA - 2025/11/04 TI - Impact of Bitcoin Returns on U.S. Gold Using ARIMA and LSTM Models BT - Proceedings of the 2nd International Conference on Sustainable Business Practices and Innovative Models (ICSBPIM-2025) PB - Atlantis Press SP - 515 EP - 529 SN - 2352-5428 UR - https://doi.org/10.2991/978-94-6463-872-1_33 DO - 10.2991/978-94-6463-872-1_33 ID - Kumar2025 ER -