Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Juwon, Lee, Hyunwook, Jeon, Hyotaek, Jin, Seungmin, Ko, Sungahn
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.15040
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918143703646208
author Kim, Juwon
Lee, Hyunwook
Jeon, Hyotaek
Jin, Seungmin
Ko, Sungahn
author_facet Kim, Juwon
Lee, Hyunwook
Jeon, Hyotaek
Jin, Seungmin
Ko, Sungahn
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15040
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Patterns to Predictions: A Shapelet-Based Framework for Directional Forecasting in Noisy Financial Markets
Kim, Juwon
Lee, Hyunwook
Jeon, Hyotaek
Jin, Seungmin
Ko, Sungahn
Machine Learning
Artificial Intelligence
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.
title From Patterns to Predictions: A Shapelet-Based Framework for Directional Forecasting in Noisy Financial Markets
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.15040