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

Paper: arXiv 2601.19504

Authors: Varun Narayan Kannan Pillai, Akshay Ajith, Sumesh K J

Abstract

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.

Complexity vs Empirical Score

• Math Complexity: 2.5/10
• Empirical Rigor: 6.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper presents an applied hybrid trading system combining standard technical indicators, FinBERT sentiment filtering, dynamic position sizing via ATR, and XGBoost classification. While empirically tested on 100 S&P 500 stocks with positive results, it lacks original mathematical modeling or deep theoretical novelty, functioning primarily as an integration of established quant techniques.

Research Flowchart

  flowchart TD
    A[Research Goal: Develop Regime-Adaptive<br>Hybrid AI Trading Strategy] --> B[Data Inputs: Historical Equity Prices<br>& Financial Text/News]
    
    subgraph C[Feature Extraction & Sentiment]
        C1[Technical Indicators:<br>EMA, MACD, RSI, Bollinger]
        C2[Market Sentiment:<br>FinBERT NLP Model]
    end
    
    B --> C
    
    C --> D[ML Signal Generation:<br>XGBoost Model]
    
    D --> E[Dynamic Risk Management:<br>Volatility & Regime Filtering]
    
    E --> F[Key Outcomes: 135.49% Return,<br>$235.5k Final Portfolio,<br>Outperformed S&P 500 & NASDAQ]