A Regime-Adaptive Equity Strategy Combining Indicators, Sentiment, and Machine Learning

Summary

The paper describes an equity trading system that combines trend and momentum signals from exponential moving averages and MACD with mean-reversion signals from RSI and Bollinger Bands. It adds financial sentiment estimates from FinBERT, uses XGBoost to generate signals, and filters or adjusts exposure according to volatility and return conditions. The design aims to adapt when market regimes change and conventional trend-following or mean-reversion approaches may struggle.

For a 24-month period, the document reports a final portfolio value of $235,492.83 and a return of 135.49% on the initial investment. It also claims outperformance over the S&P 500 and NASDAQ-100, with lower downside risk. The excerpt does not specify the dates, starting capital, instruments, transaction costs, validation design, or risk statistics, so these figures alone do not establish robustness or deployability. The reported performance should be read as a result from the described evaluation, not as a general expectation.

Key ideas

• The system combines trend and momentum indicators with mean-reversion indicators to generate equity signals.
• FinBERT sentiment analysis and XGBoost are included in the signal-generation process.
• Volatility and return environments guide regime filtering and exposure adjustment.
• The paper reports a 135.49% return over 24 months and outperformance of two equity benchmarks, but the excerpt omits evaluation details.

Tags

# 2601.19504


# Generating Alpha: A Hybrid AI-Driven Trading System Integrating Technical Analysis, Machine Learning and Financial Sentiment for Regime-Adaptive Equity Strategies









The intricate behavior patterns of financial markets are influenced by fundamental, technical, and psychological factors. During times of high volatility and regime shifts causes many traditional strategies like trend-following or mean-reversion to fail. This paper proposes a hybrid AI-based trading strategy that combines (1) trend-following and directional momentum capture via EMA and MACD, (2) detection of price normalization through mean-reversion using RSI and Bollinger Bands, (3) market psychological interpretation through sentiment analysis using FinBERT, (4) signal generation through machine learning using XGBoost and (5)dynamically adjusting exposure with market regime filtering based on volatility and return environments. The system achieved a final portfolio value of $235,492.83, yielding a return of 135.49% on initial investment over a period of 24 months. The hybrid model outperformed major benchmark indexes like S&P 500 and NASDAQ-100 over the same period showing strong flexibility and lower downside risk with superior profits validating the use of multi-modal AI in algorithmic trading.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.