DA-SPS: A Dual-stage Network based on Singular Spectrum Analysis, Patching-strategy and Spearman-correlation for Multivariate Time-series Prediction

2026-01-29

AI Summary

This work addresses the limitations of existing methods in multivariate time series forecasting, which often inadequately model the influence of exogenous variables and struggle to capture complex temporal patterns. To overcome these challenges, the authors propose DA-SPS, a dual-stage network. In the first stage, a P-Conv-LSTM architecture—integrating singular spectrum analysis (SSA), LSTM, and a patching strategy—decomposes and extracts trend and seasonal components from the target series. In the second stage, strongly correlated exogenous variables are selected via Spearman correlation, and their dynamic impacts are modeled using an L-Attention module that combines LSTM with attention mechanisms. The final prediction is generated by weighted fusion of outputs from both stages. Experiments on four public benchmarks demonstrate superior performance over state-of-the-art models, and practical efficacy is further validated on an in-house dataset of laptop motherboard test records.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Multivariate time-series forecasting, as a typical problem in the field of time series prediction, has a wide range of applications in weather forecasting, traffic flow prediction, and other scenarios. However, existing works do not effectively consider the impact of extraneous variables on the prediction of the target variable. On the other hand, they fail to fully extract complex sequence information based on various time patterns of the sequences. To address these drawbacks, we propose a DA-SPS model, which adopts different modules for feature extraction based on the information characteristics of different variables. DA-SPS mainly consists of two stages: the target variable processing stage (TVPS) and the extraneous variables processing stage (EVPS). In TVPS, the model first uses Singular Spectrum Analysis (SSA) to process the target variable sequence and then uses Long Short-Term Memory (LSTM) and P-Conv-LSTM which deploys a patching strategy to extract features from trend and seasonality components, respectively. In EVPS, the model filters extraneous variables that have a strong correlation with the target variate by using Spearman correlation analysis and further analyses them using the L-Attention module which consists of LSTM and attention mechanism. Finally, the results obtained by TVPS and EVPS are combined through weighted summation and linear mapping to produce the final prediction. The results on four public datasets demonstrate that the DA-SPS model outperforms existing state-of-the-art methods. Additionally, its performance in real-world scenarios is further validated using a private dataset collected by ourselves, which contains the test items'information on laptop motherboards.

Problem

• multivariate time-series forecasting
• extraneous variables
• time patterns
• sequence information extraction

Innovation

• Singular Spectrum Analysis
• Patching Strategy
• Spearman Correlation
• Dual-stage Network
• Multivariate Time-series Forecasting