Paper: arXiv 2505.19617

Authors: Dominik Stempień, Robert Ślepaczuk

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.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 9.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced statistical concepts like fractional integration (ARFIMA) and combines them with deep learning (LSTM) and hybridization techniques, indicating high mathematical complexity. It demonstrates high empirical rigor by using over two decades of daily data for S&P 500 and nearly ten years for Bitcoin, implementing a novel three-fold dynamic cross-validation, and evaluating both forecast accuracy and real-world trading performance with multiple risk-adjusted metrics.

Research Flowchart

  flowchart TD
  A["Research Goal: Develop & Evaluate Hybrid Models for Financial Forecasting"]
  B["Data: S&P 500 (20+ yrs) & Bitcoin (10+ yrs)"]
  C["Methodology: 3-Fold Dynamic Cross-Validation & Hyperparameter Tuning"]
  D["Models: Econometric + ML/DL<br/>(ARIMA/ARFIMA + SVM/XGBoost/LSTM)"]
  E["Non-Additive Hybrid Construction"]
  F["Evaluation: Forecast Errors & Trading Metrics"]
  G["Key Findings: Hybrid Models Outperform Benchmarks<br/>Best: ARIMA + (SVM or LSTM)"]

  A --> B
  B --> C
  C --> D
  D --> E
  E --> F
  F --> G

Cited References (98)

  1. Predicting Prices Of S&P 500 Index Using Classical Methods and Recurrent Neural Networks (2024) — link
  2. Data-driven price trends prediction of Ethereum: A hybrid machine learning and signal processing approach (2024) — link
  3. LSTM-ARIMA as a hybrid approach in algorithmic investment strategies — → 2406.18206
  4. Machine learning Ethereum cryptocurrency prediction and knowledge-based investment strategies (2024) — link
  5. RNN-LSTM: From applications to modeling techniques and beyond—Systematic review (2024) — link
  6. Supervised autoencoder MLP for financial time series forecasting — → 2404.01866
  7. Return prediction by machine learning for the Korean stock market (2023) — link
  8. Forecasting cryptocurrencies volatility using statistical and machine learning methods: A comparative study (2023) — link
and 90 more
  1. Application of machine learning in algorithmic investment strategies on global stock markets (2023) — link
  2. A review on drawdown risk measures and their implications for risk management (2022) — link
  3. LSTM in Algorithmic Investment Strategies on BTC and S&P500 Index (2022) — link
  4. Applying Hybrid ARIMA-SGARCH in Algorithmic Investment Strategies on S&P500 Index (2022) — link
  5. Stock Market Prediction Using Machine Learning Techniques: A Decade Survey on Methodologies, Recent Developments, and Future Directions (2021) — link
  6. Long memory and efficiency of Bitcoin during COVID-19 (2021) — link
  7. Efficiency in cryptocurrency markets: new evidence (2021) — link
  8. Forecasting gold price with the XGBoost algorithm and SHAP interaction values (2021) — link
  9. Forecasting mid-price movement of Bitcoin futures using machine learning (2021) — link
  10. Machine Learning and Traditional Econometric Models: A Systematic Mapping Study (2021) — link
  11. Predictions of bitcoin prices through machine learning based frameworks (2021) — link
  12. Portfolio optimization with return prediction using deep learning and machine learning (2021) — link
  13. Nvidia’s Stock Returns Prediction Using Machine Learning Techniques for Time Series Forecasting Problem (2021) — link
  14. Stock market movement forecast: A Systematic review (2020) — link
  15. Deep Learning for Price Movement Prediction Using Convolutional Neural Network and Long Short-Term Memory (2020) — link
  16. Fractional Neuro-Sequential ARFIMA-LSTM for Financial Market Forecasting (2020) — link
  17. Adaptive market hypothesis: An empirical analysis of time –varying market efficiency of cryptocurrencies (2020) — link
  18. Beyond Econometrics: A Roadmap Towards Financial Machine Learning (2019) — link
  19. Volatility in the Cryptocurrency Market (2019) — link
  20. Combining Principal Component Analysis, Discrete Wavelet Transform and XGBoost to trade in the financial markets (2019) — link
  21. Time Series Classification of Cryptocurrency Price Trend Based on a Recurrent LSTM Neural Network (2019)
  22. Momentum and contrarian effects on the cryptocurrency market (2019) — link
  23. Stock Market Analysis: A Review and Taxonomy of Prediction Techniques (2019) — link
  24. An Empirical Study of Machine Learning Algorithms for Stock Daily Trading Strategy (2019) — link
  25. Public Mood–Driven Asset Allocation: the Importance of Financial Sentiment in Portfolio Management (2018) — link
  26. A New Hybrid Method for China’s Energy Supply Security Forecasting Based on ARIMA and XGBoost (2018) — link
  27. Predicting the Price of Bitcoin Using Machine Learning (2018) — link
  28. Advances in Financial Machine Learning: Lecture 10/10 (Presentation Slides) (2018) — link
  29. Machine Learning Methods in Algorithmic Trading Strategy Optimization – Design and Time Efficiency (2018) — link
  30. Deep learning with long short-term memory networks for financial market predictions (2017) — link
  31. Time-varying long-term memory in Bitcoin market (2017) — link
  32. Stock market one-day ahead movement prediction using disparate data sources (2017) — link
  33. A deep learning framework for financial time series using stacked autoencoders and long-short term memory (2017) — link
  34. Bridging the divide in financial market forecasting: machine learners vs. financial economists (2016) — link
  35. XGBoost: A Scalable Tree Boosting System (2016) — link
  36. Backtest Overfitting in Financial Markets (2016)
  37. The Future of Empirical Finance (2015) — link
  38. Recurrent neural network and a hybrid model for prediction of stock returns (2015) — link
  39. LSTM: A Search Space Odyssey (2015) — link
  40. Forecasting stock index returns using ARIMA-SVM, ARIMA-ANN, and ARIMA-random forest hybrid models (2014) — link
  41. A hybrid ARFIMA and neural network model for electricity price prediction (2014) — link
  42. Stock index forecasting based on a hybrid model (2012) — link
  43. Improvement in Forecasting Accuracy Using the Hybrid Model of ARFIMA and Feed Forward Neural Network (2012) — link
  44. Examining Sharp, Sortino and Sterling Ratios in Portfolio Management, Evidence from Tehran Stock Exchange (2011) — link
  45. Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm (2011) — link
  46. Calculating and Comparing Security Returns is Harder than you Think: A Comparison between Logarithmic and Simple Returns (2010) — link
  47. Modelling Exchange Rate Returns Using Non-linear Models (2010) — link
  48. Surveying stock market forecasting techniques - Part II: Soft computing methods (2009) — link
  49. Short term forecasting with support vector machines and application to stock price prediction (2008) — link
  50. Long memory in the Portuguese stock market (2007) — link
  51. Dependence and mean reversion in stock prices: The case of the MENA region (2006) — link
  52. An empirical investigation of the usefulness of ARFIMA models for predicting macroeconomic and financial time series (2006) — link
  53. A hybrid ARIMA and support vector machines model in stock price forecasting (2005) — link
  54. Rational bubbles or persistent deviations from market fundamentals (2005) — link
  55. Forecasting stock market movement direction with support vector machine (2005) — link
  56. 2005 Special Issue: A comparative study of autoregressive neural network hybrids (2005) — link
  57. Model-order selection: a review of information criterion rules (2004) — link
  58. The Efficient Market Hypothesis and Its Critics (2003) — link
  59. Financial time series forecasting using support vector machines (2003) — link
  60. Learning Precise Timing with LSTM Recurrent Networks (2003) — link
  61. Financial Forecasting Using Support Vector Machines (2001) — link
  62. Support vector machines: hype or hallelujah? (2000) — link
  63. Learning to Forget: Continual Prediction with LSTM (2000) — link
  64. Long memory in the Greek stock market (2000) — link
  65. Combined forecasts from linear and nonlinear time series models (1999) — link
  66. A Brief Introduction to Boosting (1999)
  67. Long Short-Term Memory (1997) — link
  68. A decision-theoretic generalization of on-line learning and an application to boosting (1997) — link
  69. Varieties of long memory models (1996) — link
  70. Support-Vector Networks (1995) — link
  71. A search for long memory in international stock market returns (1995) — link
  72. Long-Term Memory in Stock Market Prices (1991) — link
  73. Forecasting, Structural Time Series Models and the Kalman Filter (1990) — link
  74. The Principles of the Box-Jenkins Approach (1975) — link
  75. Spurious regressions in econometrics (1974) — link
  76. Time series analysis, forecasting and control (1972) — link
  77. Understanding support vector machine regression (2025)
  78. Cryptocurrency price forecasting–a comparative analysis of ensemble learning and deep learning methods (2024)
  79. ARIMA vs LSTM on NASDAQ stock exchange data (2022) — link
  80. Prediction-Based Portfolio Optimization Models Using Deep Neural Networks (2020) — link
  81. Fore-casting stock market crisis events using deep and statistical machine learning techniques (2018)
  82. STOCK-MARKET FORECASTING USING MACHINE LEARNING (2017)
  83. PSEUDO-MATHEMATICS AND FINANCIALCHARLATANISM: THE EFFECTS OF BACKTEST OVERFITTING ONOUT-OF-SAMPLE PERFORMANCE (2014) — link
  84. MUTUAL FUND PERFORMANCE* (2007) — link
  85. 25 years of time series forecasting (2006) — link
  86. To combine or not to combine: selecting among forecasts and their combinations (2005) — link
  87. Time series forecasting using a hybrid ARIMA and neural network model (2003) — link
  88. AN INTRODUCTION TO LONG‐MEMORY TIME SERIES MODELS AND FRACTIONAL DIFFERENCING (1980) — link
  89. Efficient capital markets (1970)
  90. International Journal of Uncertainty, Fuzziness and Knowledge-based Systems F the Vanishing Gradient Problem during Learning Recurrent Neural Nets and Problem Solutions

2 of 98 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.