Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series Classification

In this paper, the authors introduce a novel feature extraction method based on pattern detection in financial data to enhance the performance of deep learning models for financial time series classification. Existing financial forecasting models often struggle with the inherent volatility and compl...

Full description

Saved in:
Bibliographic Details
Main Authors: Seyed Ali Hosseini, Francesco Grimaccia, Alessandro Niccolai, Silvia Trimarchi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11058928/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849420925047406592
author Seyed Ali Hosseini
Francesco Grimaccia
Alessandro Niccolai
Silvia Trimarchi
author_facet Seyed Ali Hosseini
Francesco Grimaccia
Alessandro Niccolai
Silvia Trimarchi
author_sort Seyed Ali Hosseini
collection DOAJ
description In this paper, the authors introduce a novel feature extraction method based on pattern detection in financial data to enhance the performance of deep learning models for financial time series classification. Existing financial forecasting models often struggle with the inherent volatility and complexity of financial markets, particularly due to their reliance on traditional financial data features which fail to capture intricate price patterns. This research addresses the critical gap in effectively identifying and leveraging these patterns to improve predictive accuracy. By collecting tick-by-tick data from the European Carbon Emission Allowance market and resampling it to a 15-minute timeframe, we developed a method to detect pivotal price patterns and extract relevant features. Integrating these features with traditional open, high, low, close, and volume (OHLCV) data in long-short-term memory (LSTM) and gated recurrent unit (GRU) combined with dense neural networks, our empirical results demonstrate significant improvements in model performance, showcasing enhanced accuracy compared to models using only traditional data features.
format Article
id doaj-art-264d10b752ae4d5ebffa38eb57f9977e
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-264d10b752ae4d5ebffa38eb57f9977e2025-08-20T03:31:37ZengIEEEIEEE Access2169-35362025-01-011311334311335510.1109/ACCESS.2025.358425111058928Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series ClassificationSeyed Ali Hosseini0https://orcid.org/0009-0005-5296-4009Francesco Grimaccia1https://orcid.org/0000-0003-2568-9927Alessandro Niccolai2https://orcid.org/0000-0002-5840-4222Silvia Trimarchi3https://orcid.org/0000-0001-5741-7833Department of Energy, Polytechnic University of Milan, Milan, ItalyDepartment of Energy, Polytechnic University of Milan, Milan, ItalyDepartment of Energy, Polytechnic University of Milan, Milan, ItalyDepartment of Energy, Polytechnic University of Milan, Milan, ItalyIn this paper, the authors introduce a novel feature extraction method based on pattern detection in financial data to enhance the performance of deep learning models for financial time series classification. Existing financial forecasting models often struggle with the inherent volatility and complexity of financial markets, particularly due to their reliance on traditional financial data features which fail to capture intricate price patterns. This research addresses the critical gap in effectively identifying and leveraging these patterns to improve predictive accuracy. By collecting tick-by-tick data from the European Carbon Emission Allowance market and resampling it to a 15-minute timeframe, we developed a method to detect pivotal price patterns and extract relevant features. Integrating these features with traditional open, high, low, close, and volume (OHLCV) data in long-short-term memory (LSTM) and gated recurrent unit (GRU) combined with dense neural networks, our empirical results demonstrate significant improvements in model performance, showcasing enhanced accuracy compared to models using only traditional data features.https://ieeexplore.ieee.org/document/11058928/Energy marketfinancial pattern extractionfinancial feature extractiondeep learningfinancial data classification
spellingShingle Seyed Ali Hosseini
Francesco Grimaccia
Alessandro Niccolai
Silvia Trimarchi
Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series Classification
IEEE Access
Energy market
financial pattern extraction
financial feature extraction
deep learning
financial data classification
title Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series Classification
title_full Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series Classification
title_fullStr Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series Classification
title_full_unstemmed Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series Classification
title_short Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series Classification
title_sort pattern based feature extraction for improved deep learning in financial time series classification
topic Energy market
financial pattern extraction
financial feature extraction
deep learning
financial data classification
url https://ieeexplore.ieee.org/document/11058928/
work_keys_str_mv AT seyedalihosseini patternbasedfeatureextractionforimproveddeeplearninginfinancialtimeseriesclassification
AT francescogrimaccia patternbasedfeatureextractionforimproveddeeplearninginfinancialtimeseriesclassification
AT alessandroniccolai patternbasedfeatureextractionforimproveddeeplearninginfinancialtimeseriesclassification
AT silviatrimarchi patternbasedfeatureextractionforimproveddeeplearninginfinancialtimeseriesclassification