A Novel Decision Ensemble Framework: Customized Attention-BiLSTM and XGBoost for Speculative Stock Price Forecasting

ArXiv ID: 2401.11621 “View on arXiv”

Authors: Unknown

Abstract

Forecasting speculative stock prices is essential for effective investment risk management that drives the need for the development of innovative algorithms. However, the speculative nature, volatility, and complex sequential dependencies within financial markets present inherent challenges which necessitate advanced techniques. This paper proposes a novel framework, CAB-XDE (customized attention BiLSTM-XGB decision ensemble), for predicting the daily closing price of speculative stock Bitcoin-USD (BTC-USD). CAB-XDE framework integrates a customized bi-directional long short-term memory (BiLSTM) with the attention mechanism and the XGBoost algorithm. The customized BiLSTM leverages its learning capabilities to capture the complex sequential dependencies and speculative market trends. Additionally, the new attention mechanism dynamically assigns weights to influential features, thereby enhancing interpretability, and optimizing effective cost measures and volatility forecasting. Moreover, XGBoost handles nonlinear relationships and contributes to the proposed CAB-XDE framework robustness. Additionally, the weight determination theory-error reciprocal method further refines predictions. This refinement is achieved by iteratively adjusting model weights. It is based on discrepancies between theoretical expectations and actual errors in individual customized attention BiLSTM and XGBoost models to enhance performance. Finally, the predictions from both XGBoost and customized attention BiLSTM models are concatenated to achieve diverse prediction space and are provided to the ensemble classifier to enhance the generalization capabilities of CAB-XDE. The proposed CAB-XDE framework is empirically validated on volatile Bitcoin market, sourced from Yahoo Finance and outperforms state-of-the-art models with a MAPE of 0.0037, MAE of 84.40, and RMSE of 106.14.

Keywords: Bidirectional LSTM (BiLSTM), XGBoost, Attention Mechanism, Bitcoin Price Prediction, Ensemble Learning, Cryptocurrency

Complexity vs Empirical Score

• Math Complexity: 6.0/10
• Empirical Rigor: 7.5/10
• Quadrant: Holy Grail
• Why: The paper employs advanced deep learning architectures (BiLSTM, attention mechanisms, XGBoost) with a custom ensemble method, indicating high mathematical complexity; it is highly empirical, validated on real Bitcoin market data with specific performance metrics (MAPE, MAE, RMSE) and a defined dataset, qualifying it as backtest-ready.

  flowchart TD
    A["Research Goal: Forecast Speculative Stock Prices<br>Bitcoin-USD Closing Price"] --> B["Data & Inputs<br>Yahoo Finance: BTC-USD Daily Data"]
    
    B --> C["Core Methodology: CAB-XDE Framework"]
    
    subgraph C ["CAB-XDE Framework"]
        C1["Customized Attention BiLSTM<br>Capture Sequential Dependencies"] --> C2["Weight Determination Theory<br>Iterative Error Reciprocal Adjustment"]
        C3["XGBoost<br>Handle Nonlinear Relationships"] --> C2
        C2 --> C4["Decision Ensemble<br>Concatenate Predictions & Ensemble Classifier"]
    end
    
    C --> D["Computational Process<br>Model Training & Validation"]
    
    D --> E["Key Findings/Outcomes<br>MAPE: 0.0037, MAE: 84.40, RMSE: 106.14<br>Outperforms State-of-the-Art Models"]