From Patterns to Predictions: A Shapelet-Based Framework for Directional Forecasting in Noisy Financial Markets

2025-09-18

AI Summary

Financial market direction forecasting demands both high accuracy and model interpretability: conventional pattern-based methods suffer from ill-defined structures and poor generalization, while deep learning models lack transparency. To address this, we propose a two-stage interpretable forecasting framework. First, SIMPC performs unsupervised segmentation clustering on multivariate time series; second, JISC-Net learns scale- and time-invariant shapelets—marking the first application of shapelets to financial time series direction prediction—enabling pattern-driven, local-to-global interpretable inference. Evaluated on 12 indicator–dataset combinations across Bitcoin and three S&P 500 stocks, our method achieves state-of-the-art or second-best performance in 11 cases, significantly outperforming mainstream baselines. Crucially, it maintains high predictive accuracy while explicitly identifying salient local morphological patterns driving each forecast—thus achieving a rare synergy of strong performance and intrinsic interpretability.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Directional forecasting in financial markets requires both accuracy and interpretability. Before the advent of deep learning, interpretable approaches based on human-defined patterns were prevalent, but their structural vagueness and scale ambiguity hindered generalization. In contrast, deep learning models can effectively capture complex dynamics, yet often offer limited transparency. To bridge this gap, we propose a two-stage framework that integrates unsupervised pattern extracion with interpretable forecasting. (i) SIMPC segments and clusters multivariate time series, extracting recurrent patterns that are invariant to amplitude scaling and temporal distortion, even under varying window sizes. (ii) JISC-Net is a shapelet-based classifier that uses the initial part of extracted patterns as input and forecasts subsequent partial sequences for short-term directional movement. Experiments on Bitcoin and three S&P 500 equities demonstrate that our method ranks first or second in 11 out of 12 metric--dataset combinations, consistently outperforming baselines. Unlike conventional deep learning models that output buy-or-sell signals without interpretable justification, our approach enables transparent decision-making by revealing the underlying pattern structures that drive predictive outcomes.

Problem

• Bridging accuracy and interpretability in financial directional forecasting
• Extracting recurrent patterns invariant to scaling and distortion
• Providing transparent pattern-based justification for market predictions

Innovation

• Unsupervised pattern extraction from time series
• Shapelet-based classifier for directional forecasting
• Transparent decision-making with interpretable pattern structures