Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Long, Hou-Wan, Ho, On-In, He, Qi-Qiao, Si, Yain-Whar
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.00378
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912302322679808
author Long, Hou-Wan
Ho, On-In
He, Qi-Qiao
Si, Yain-Whar
author_facet Long, Hou-Wan
Ho, On-In
He, Qi-Qiao
Si, Yain-Whar
contents In financial analysis, time series modeling is often hampered by data scarcity, limiting neural network models' ability to generalize. Transfer learning mitigates this by leveraging data from similar domains, but selecting appropriate source domains is crucial to avoid negative transfer. This study enhances source domain selection in transfer learning by introducing Gramian Angular Field (GAF) transformations to improve time series similarity functions. We evaluate a comprehensive range of baseline similarity functions, including both basic and state-of-the-art (SOTA) functions, and perform extensive experiments with Deep Neural Networks (DNN) and Long Short-Term Memory (LSTM) networks. The results demonstrate that GAF-based similarity functions significantly reduce prediction errors. Notably, Coral (GAF) for DNN and CMD (GAF) for LSTM consistently deliver superior performance, highlighting their effectiveness in complex financial environments.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00378
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transfer Learning in Financial Time Series with Gramian Angular Field
Long, Hou-Wan
Ho, On-In
He, Qi-Qiao
Si, Yain-Whar
Computational Engineering, Finance, and Science
In financial analysis, time series modeling is often hampered by data scarcity, limiting neural network models' ability to generalize. Transfer learning mitigates this by leveraging data from similar domains, but selecting appropriate source domains is crucial to avoid negative transfer. This study enhances source domain selection in transfer learning by introducing Gramian Angular Field (GAF) transformations to improve time series similarity functions. We evaluate a comprehensive range of baseline similarity functions, including both basic and state-of-the-art (SOTA) functions, and perform extensive experiments with Deep Neural Networks (DNN) and Long Short-Term Memory (LSTM) networks. The results demonstrate that GAF-based similarity functions significantly reduce prediction errors. Notably, Coral (GAF) for DNN and CMD (GAF) for LSTM consistently deliver superior performance, highlighting their effectiveness in complex financial environments.
title Transfer Learning in Financial Time Series with Gramian Angular Field
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2504.00378