The Accuracy Paradox in AI Equity Markets: A Regime-AwareTrading Strategy using XGBoost and Walk-Forward Optimization
DOI:
https://doi.org/10.37591/njfpm.v9i2.2059Keywords:
Algorithmic Trading, XGBoost, VIX, Tech Stocks, Risk ManagementAbstract
This study investigates the “Accuracy Paradox” in algorithmic equity trading by examining whether a machine learning model with near-random directional prediction accuracy can still generate profitable trading outcomes when combined with effective risk- management and market-regime rules. An XGBoost classifier was developed and evaluated using approximately six years of daily market data from five major technology stocks—NVIDIA, Apple, Microsoft, Alphabet, and Meta—covering the period from January 2020 to February 2026. The model incorporated twelve predictors based on technical indicators, including moving averages, RSI, MACD, rate of change, Bollinger Band position, volatility measures, and VIX-based sentiment proxies. A regime-aware trading framework was implemented using a 200-day simple moving average filter, a probability threshold for trade execution, a 2% stop-loss, a 4% take-profit target, and transaction costs. Walk-forward optimization with rolling training and testing windows was employed to reduce look-ahead bias and assess the robustness of the strategy. The results show that XGBoost achieved an average directional accuracy of approximately 49.8%, yet the resulting trading strategy generated positive returns in four of the five stocks. Meta produced the highest return of 32%, followed by Microsoft at 18%, Alphabet at 17%, and Apple at 5%, while NVIDIA recorded a loss of 13%. The findings indicate that predictive accuracy alone may not determine trading profitability and that regime filtering, disciplined trade execution, and asymmetric risk management can play a more important role in controlling losses and improving portfolio performance.
References
1. Chen, T., Guestrin, C.: XGBoost: A Scalable Tree Boosting System. In: KDD 2016, pp. 785–794. ACM (2016)
2. Fama, E.F.: Efficient Capital Markets: A Review of Theory and Empirical Work. J. Finance 25(2), 383–417 (1970)
3. Bollen, J., Mao, H., Zeng, X.: Twitter Mood Predicts the Stock Market. J. Computational Science 2(1), 1–8 (2011)
4. Malkiel, B.G.: A Random Walk Down Wall Street. W.W. Norton, New York (2003)
5. Basak, S., et al.: Predicting Stock Prices Using Tree-Based Classifiers. N. Am, J. Econ. Finance 47, 552–567 (2019)
6. Patel, J., et al.: Predicting Stock Movement Using ML Techniques. Expert Syst. Appl. 42(1), 259–268 (2015)
7. Cavalcante, R.C., et al.: Computational Intelligence and Financial Markets: A Survey. Expert Syst. Appl. 55, 194–211 (2016)
8. Lopez de Prado, M.: Advances in Financial Machine Learning. Wiley (2018)
9. Kara, Y., et al.: Predicting Stock Price Direction Using ANN and SVM. Expert Syst. Appl. 38(5), 5311–5319 (2011)
10. Shah, D., et al.: Stock Market Analysis: A Review and Taxonomy. Int. J. Financial Studies 7(2), 26 (2019)
11. Shiller, R.J.: Irrational Exuberance. Princeton University Press (2015)
12. Kahneman, D., Tversky, A.: Prospect Theory: An Analysis of Decision under Risk. Econometrica 47(2), 263–291 (1979)
13. Whaley, R.E.: The Investor Fear Gauge. J. Portfolio Management 26(3), 12–17(2000)
14. Fischer, T., Krauss, C.: Deep Learning with Long Short-Term Memory Networks for Financial Market Predictions. Eur. J. Operational Research 270(2), 654–669(2018)
15. Jegadeesh, N., Titman, S.: Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency. J. Finance 48(1), 65–91 (1993)
16. Lo, A.W.: The Adaptive Markets Hypothesis. J. Portfolio Management 30(5), 15–29 (2004)
17. Anghel Che, C., et al.: Multi-Agent Systems in Algorithmic Trading. Econ. Insights71, 21–32 (2019)
