Hybrid Models for Financial Forecasting: Combining Econometric, Machine Learning, and Deep Learning Models

TL;DR

This paper develops and evaluates hybrid financial forecasting models combining econometric, machine learning, and deep learning techniques, demonstrating improved performance over individual models and benchmarks across different assets and market conditions.

Contribution

It introduces a systematic approach to hybrid modeling using a novel cross-validation method and evaluates their effectiveness on real financial data, highlighting the importance of model construction.

Findings

Hybrid models outperform individual models and benchmarks.

ARIMA combined with SVM or LSTM yields the best results.

Proper hybrid model construction enhances trading profitability.

Abstract

This research systematically develops and evaluates various hybrid modeling approaches by combining traditional econometric models (ARIMA and ARFIMA models) with machine learning and deep learning techniques (SVM, XGBoost, and LSTM models) to forecast financial time series. The empirical analysis is based on two distinct financial assets: the S&P 500 index and Bitcoin. By incorporating over two decades of daily data for the S&P 500 and almost ten years of Bitcoin data, the study provides a comprehensive evaluation of forecasting methodologies across different market conditions and periods of financial distress. Models' training and hyperparameter tuning procedure is performed using a novel three-fold dynamic cross-validation method. The applicability of applied models is evaluated using both forecast error metrics and trading performance indicators. The obtained findings indicate that the proper construction process of hybrid models plays a crucial role in developing profitable trading strategies, outperforming their individual components and the benchmark Buy&Hold strategy. The most effective hybrid model architecture was achieved by combining the econometric ARIMA model with either SVM or LSTM, under the assumption of a non-additive relationship between the linear and nonlinear components.