Deep Learning-Based Financial Time Series Forecasting via Sliding Window and Variational Mode Decomposition
This is an incremental improvement for financial forecasting applications.
The paper tackled financial time series forecasting by combining variational mode decomposition (VMD) with an LSTM model, resulting in improved performance and stability compared to using raw data.
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.