Saved in:
Bibliographic Details
Main Author: Li, Luke
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.12565
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918128168992768
author Li, Luke
author_facet Li, Luke
contents To address the complexity of financial time series, this paper proposes a forecasting model combining sliding window and variational mode decomposition (VMD) methods. Historical stock prices and relevant market indicators are used to construct datasets. VMD decomposes non-stationary financial time series into smoother subcomponents, improving model adaptability. The decomposed data is then input into a deep learning model for prediction. The study compares the forecasting effects of an LSTM model trained on VMD-processed sequences with those using raw time series, demonstrating better performance and stability.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12565
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Learning-Based Financial Time Series Forecasting via Sliding Window and Variational Mode Decomposition
Li, Luke
Machine Learning
To address the complexity of financial time series, this paper proposes a forecasting model combining sliding window and variational mode decomposition (VMD) methods. Historical stock prices and relevant market indicators are used to construct datasets. VMD decomposes non-stationary financial time series into smoother subcomponents, improving model adaptability. The decomposed data is then input into a deep learning model for prediction. The study compares the forecasting effects of an LSTM model trained on VMD-processed sequences with those using raw time series, demonstrating better performance and stability.
title Deep Learning-Based Financial Time Series Forecasting via Sliding Window and Variational Mode Decomposition
topic Machine Learning
url https://arxiv.org/abs/2508.12565