Portfolio Construction Based on XGBoost-CAPM Model: Evidence from the Cryptocurrency Market
- DOI
- 10.2991/978-94-6463-459-4_16How to use a DOI?
- Keywords
- Portfolio Construction; Cryptocurrency; CAPM Model; XGBoost; Time series
- Abstract
This study investigates the construction of an optimal investment portfolio in the cryptocurrency market using the XGBoost algorithm and the CAPM model. To achieve this objective, one selected Bitcoin, Ethereum, Litecoin, and Tether as representative assets in the cryptocurrency market and used the CMC200 as the market index. The study primarily employed the XGBoost algorithm to predict the returns of the market index, while using the CAPM model and OLS regression analysis to calculate the alpha and beta of each asset. Based on the predicted market index returns and the alpha and beta values of each asset, this paper further calculated the expected returns of each asset. For portfolio optimization strategies, one used the maximum Sharpe ratio and minimum volatility as optimization goals to determine the weights of the optimal investment portfolio. The results indicate that by combining the XGBoost prediction model, CAPM theory, and portfolio optimization strategies, one can build investment portfolios in the cryptocurrency market with higher returns and lower risk, providing valuable guidance for cryptocurrency investors.
- Copyright
- © 2024 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 - Jintong Yang PY - 2024 DA - 2024/07/23 TI - Portfolio Construction Based on XGBoost-CAPM Model: Evidence from the Cryptocurrency Market BT - Proceedings of the 2024 9th International Conference on Social Sciences and Economic Development (ICSSED 2024) PB - Atlantis Press SP - 127 EP - 136 SN - 2352-5428 UR - https://doi.org/10.2991/978-94-6463-459-4_16 DO - 10.2991/978-94-6463-459-4_16 ID - Yang2024 ER -