Hybrid Vector Auto Regression and Neural Network Model for Order Flow Imbalance Prediction in High Frequency Trading

ArXiv ID: 2411.08382 “View on arXiv”

Authors: Unknown

Abstract

In high frequency trading, accurate prediction of Order Flow Imbalance (OFI) is crucial for understanding market dynamics and maintaining liquidity. This paper introduces a hybrid predictive model that combines Vector Auto Regression (VAR) with a simple feedforward neural network (FNN) to forecast OFI and assess trading intensity. The VAR component captures linear dependencies, while residuals are fed into the FNN to model non-linear patterns, enabling a comprehensive approach to OFI prediction. Additionally, the model calculates the intensity on the Buy or Sell side, providing insights into which side holds greater trading pressure. These insights facilitate the development of trading strategies by identifying periods of high buy or sell intensity. Using both synthetic and real trading data from Binance, we demonstrate that the hybrid model offers significant improvements in predictive accuracy and enhances strategic decision-making based on OFI dynamics. Furthermore, we compare the hybrid models performance with standalone FNN and VAR models, showing that the hybrid approach achieves superior forecasting accuracy across both synthetic and real datasets, making it the most effective model for OFI prediction in high frequency trading.

Keywords: Order Flow Imbalance (OFI), Vector Auto Regression (VAR), Feedforward Neural Network (FNN), High Frequency Trading (HFT), Trading Intensity, Cryptocurrencies

Complexity vs Empirical Score

• Math Complexity: 6.0/10
• Empirical Rigor: 7.5/10
• Quadrant: Holy Grail
• Why: The paper employs advanced econometric modeling (VAR) and neural networks, indicating high mathematical density, and demonstrates rigor through real-world trading data from Binance, comprehensive model comparisons, and specific metrics for strategy evaluation.

  flowchart TD
    A["Research Goal<br>Predict Order Flow Imbalance OFI in HFT"] --> B["Data Collection & Preprocessing"]
    B --> C{"Model Formulation"}
    
    C --> D["VAR Component<br>Captures Linear Dependencies"]
    C --> E["Residual Analysis<br>Extracts Non Linear Patterns"]
    
    D --> F["FNN Component<br>Models Non Linear Residuals"]
    E --> F
    
    F --> G["Hybrid VAR FNN Model<br>Combines Linear & Non Linear Predictions"]
    
    G --> H["Key Findings & Outcomes"]
    
    H --> I["Superior Accuracy<br>Hybrid outperforms standalone VAR and FNN"]
    H --> J["Trading Intensity Insights<br>Identifies Buy vs Sell Pressure"]
    H --> K["Strategic Utility<br>Facilitates HFT Strategy Development"]
    
    style A fill:#e1f5fe
    style H fill:#f3e5f5