Integrating Explainable AI for Transparent and Accurate Cryptocurrency Prediction
Abstract
The cryptocurrency market, particularly Bitcoin, is highly volatile, making accurate price prediction a crucial challenge in finance and machine learning. This study employs the Extreme Gradient Boosting algorithm to develop a robust predictive model for Bitcoin price prediction. Using historical price data and technical indicators, the model captures intricate market patterns and enhances predictive accuracy. Our results indicate that XGBoost achieves a strong R-squared score of 0.9267, demonstrating high reliability for short-term forecasting. The model is trained on high-frequency historical data, incorporating features such as moving averages, the relative strength index, and Bollinger bands. To improve interpretability, we integrate Explainable AI techniques, specifically SHapley Additive ExPlanations and Local Interpretable Model-agnostic Explanations. SHAP highlights that recent closing prices significantly influence predictions, while LIME provides instance-specific explanations. By combining SHAP’s global interpretability with LIME’s localized insights, we bridge the gap between predictive accuracy and transparency. We also address potential risks such as overfitting and data leakage through rigorous cross-validation and hyperparameter tuning. Our findings suggest that XGBoost, when properly optimized and interpreted, serves as a powerful tool for short-term cryptocurrency price forecasting. This study contributes to AI-driven financial analytics, offering valuable insights for traders, analysts, and researchers seeking data-driven decision making in cryptocurrency markets.
References
[2] F. Fang, C. Ventre, M. Basios, L. Kanthan, D. Martinez-Rego, F. Wu, and L. Li, “Cryptocurrency trading: a comprehensive survey,” Financial Innova- tion, vol. 8, no. 1, p. 13, 2022.
[3] D. Yermack, “Is bitcoin a real currency? an economic appraisal,” in Handbook of digital currency. Elsevier, 2024, pp. 29–40.
[4] N. Kyriazis, S. Papadamou, and S. Corbet, “A sys- tematic review of the bubble dynamics of cryptocur- rency prices,” Research in International Business and Finance, vol. 54, p. 101254, 2020.
[5] N. Abu Bakar and S. Rosbi, “Autoregressive inte- grated moving average (arima) model for forecasting cryptocurrency exchange rate in high volatility envi- ronment: A new insight of bitcoin transaction,” Inter- national Journal of Advanced Engineering Research and Science, vol. 4, no. 11, pp. 130–137, 2017.
[6] Q. Phung Duy, O. Nguyen Thi, P. H. Le Thi, H. D. Pham Hoang, K. L. Luong, and K. N. Nguyen Thi, “Estimating and forecasting bitcoin daily prices us- ing arima-garch models,” Business Analyst Journal, vol. 45, no. 1, pp. 11–23, 2024.
[7] P. Giudici and I. Abu-Hashish, “What determines bitcoin exchange prices? a network var approach,” Finance Research Letters, vol. 28, pp. 309–318, 2019.
[8] E. K. Sahin, “Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using xgboost, gradient boosting machine, and random forest,” SN Applied Sciences, vol. 2, no. 7, p. 1308, 2020.
[9] P. Biecek and T. Burzykowski, “Local interpretable model-agnostic explanations (lime),” Explanatory Model Analysis Explore, Explain and Examine Pre- dictive Models, vol. 1, pp. 107–124, 2021.
[10] K. E. Mokhtari, B. P. Higdon, and A. Bas ̧ar, “Inter- preting financial time series with shap values,” in Pro- ceedings of the 29th annual international conference on computer science and software engineering, 2019, pp. 166–172.
[11] B. Quinn, “Explaining ai in finance: Past, present, prospects,” arXiv preprint arXiv:2306.02773, 2023.
[12] R. Dwivedi, D. Dave, H. Naik, S. Singhal, R. Omer, P. Patel, B. Qian, Z. Wen, T. Shah, G. Morgan et al., “Explainable ai (xai): Core ideas, techniques, and solutions,” ACM Computing Surveys, vol. 55, no. 9, pp. 1–33, 2023.
[13] P.-D. Arsenault, S. Wang, and J.-M. Patenaude, “A survey of explainable artificial intelligence (xai) in financial time series forecasting,” ACM Computing Surveys, 2024.
[14] Y. Gao, S. Gu, J. Jiang, S. R. Hong, D. Yu, and L. Zhao, “Going beyond xai: A systematic survey for explanation-guided learning,” ACM Computing Surveys, vol. 56, no. 7, pp. 1–39, 2024.
[15] C. Rudin, “Stop explaining black box machine learn- ing models for high stakes decisions and use inter- pretable models instead,” Nature machine intelligence, vol. 1, no. 5, pp. 206–215, 2019.
[16] C. Molnar, Interpretable machine learning. Lulu.com, 2020.
[17] N. Bussmann, P. Giudici, D. Marinelli, and J. Pa-
penbrock, “Explainable machine learning in credit risk management,” Computational Economics, vol. 57, no. 1, pp. 203–216, 2021.
[18] G. Babaei, P. Giudici, and E. Raffinetti, “Explainable fintech lending,” Journal of Economics and Business, vol. 125, p. 106126, 2023.
[19] P. N. Srinivasu, N. Sandhya, R. H. Jhaveri, and R. Raut, “From blackbox to explainable ai in health- care: existing tools and case studies,” Mobile Infor- mation Systems, vol. 2022, no. 1, p. 8167821, 2022.
[20] T. Miller, “Explanation in artificial intelligence: In- sights from the social sciences,” Artificial intelligence, vol. 267, pp. 1–38, 2019.
[21] J. Dong, S. Chen, M. Miralinaghi, T. Chen, P. Li, and S. Labi, “Why did the ai make that decision? towards an explainable artificial intelligence (xai) for autonomous driving systems,” Transportation re- search part C: emerging technologies, vol. 156, p. 104358, 2023.
[22] T. Chen, T. He, M. Benesty, V. Khotilovich, Y. Tang, H. Cho, K. Chen, R. Mitchell, I. Cano, T. Zhou et al., “Xgboost: extreme gradient boosting,” R package ver- sion 0.4-2, vol. 1, no. 4, pp. 1–4, 2015.
[23] Z. A. Ali, Z. H. Abduljabbar, H. A. Tahir, A. B. Sallow, and S. M. Almufti, “extreme gradient boosting algorithm with machine learning: A review,” Aca- demic Journal of Nawroz University, vol. 12, no. 2, pp. 320–334, 2023.
[24] A. Hafid, M. Ebrahim, M. Rahouti, and D. Oliveira, “Cryptocurrency price forecasting using xgboost re- gressor and technical indicators,” in 2024 IEEE Inter- national Performance, Computing, and Communica- tions Conference (IPCCC), 2024, pp. 1–6.
[25] M. Li, H. Sun, Y. Huang, and H. Chen, “Shapley value: from cooperative game to explainable artificial intelligence,” Autonomous Intelligent Systems, vol. 4, no. 1, p. 2, 2024.
[26] J.W.Goodell,S.B.Jabeur,F.Saaˆdaoui,andM.A. Nasir, “Explainable artificial intelligence modeling to forecast bitcoin prices,” International Review of Financial Analysis, vol. 88, p. 102702, 2023.
