Trend-encoded Probabilistic Multi-order Model: A Non-Machine Learning Approach for Enhanced Stock Market Forecasts
Peiwan Wang, Chenhao Cui, Yong Li
TL;DR
The paper introduces TeMoP, a non-parametric, trend-encoded probabilistic model that integrates forecasts from multiple lag orders to predict stock market trends. By partitioning data according to trend features, employing membership degrees, and combining likelihood-like scores across lags with Bayesian-style updates, TeMoP addresses non-stationarity and robustness issues common in time-series forecasting. Empirical tests on nine stock indices across various markets show TeMoP achieving superior accuracy, model ranking, and simulated returns compared to statistical, machine learning, and deep learning baselines, with strong robustness across data sets. The work highlights the practical value of incorporating trend information and adaptive lag fusion for real-world financial forecasting and points to extending the approach to multi-step ahead predictions.
Abstract
In recent years, the dominance of machine learning in stock market forecasting has been evident. While these models have shown decreasing prediction errors, their robustness across different datasets has been a concern. A successful stock market prediction model minimizes prediction errors and showcases robustness across various data sets, indicating superior forecasting performance. This study introduces a novel multiple lag order probabilistic model based on trend encoding (TeMoP) that enhances stock market predictions through a probabilistic approach. Results across different stock indexes from nine countries demonstrate that the TeMoP outperforms the state-of-the-art machine learning models in predicting accuracy and stabilization.