DUET

Abstract

1. Introduction

The important components of DUET: (a) Distribution Router; (b) Linear Pattern Extractor; (c) Learnable Distance Metric; (d) Fusion Module.

This code is the official PyTorch implementation of our KDD'25 paper: DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting.

News (2025.12) Time series model (DUET) was ranked 1st of the most influential papers in KDD 2025

2. Objective

[KDD 2025 Most Influential Paper] DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting

This project demonstrates how Shell, Deep Learning can be applied to a real-world Data Science problem.

4. Technology Stack

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• Linux / macOS terminal or WSL on Windows
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/decisionintelligence/DUET.git
cd DUET

1. Requirements
2. Data preparation
3. Train and evaluate model
4. To see the model structure of DUET, click here.
5. We provide all the experiment scripts for DUET and other baselines under the folder ./scripts/multivariate_forecast. For example you can reproduce all the experiment results as the following script:

pip install -r requirements.txt

sh ./scripts/multivariate_forecast/ETTh1_script/DUET.sh

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Turn the analysis into an interactive dashboard
• Automate data refresh with a scheduled job
• Add a predictive model on top of the analysis

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. What is the source of the dataset and how was missing data handled?
2. Which exploratory analysis steps revealed the most useful insight?
3. Why were these particular charts chosen to present the data?
4. Which statistical or ML technique supports the conclusions?
5. How could the analysis be automated or refreshed with new data?

9. Source Code & License

This project is developed by decisionintelligence and published on GitHub under the MIT License. Please follow the license terms and credit the original author when you use or modify this code.