ForecastGAN: A Decomposition-Based Adversarial Framework for Multi-Horizon Time Series Forecasting
This addresses forecasting limitations in domains like finance and supply chain management, offering a more generalizable approach without extensive tuning, though it appears incremental as an integration of existing techniques.
The paper tackles multi-horizon time series forecasting by introducing ForecastGAN, a decomposition-based adversarial framework that integrates numerical and categorical features. Results show it consistently outperforms state-of-the-art transformer models for short-term forecasting on eleven benchmark datasets while remaining competitive for long-term horizons.
Time series forecasting is essential across domains from finance to supply chain management. This paper introduces ForecastGAN, a novel decomposition based adversarial framework addressing limitations in existing approaches for multi-horizon predictions. Although transformer models excel in long-term forecasting, they often underperform in short-term scenarios and typically ignore categorical features. ForecastGAN operates through three integrated modules: a Decomposition Module that extracts seasonality and trend components; a Model Selection Module that identifies optimal neural network configurations based on forecasting horizon; and an Adversarial Training Module that enhances prediction robustness through Conditional Generative Adversarial Network training. Unlike conventional approaches, ForecastGAN effectively integrates both numerical and categorical features. We validate our framework on eleven benchmark multivariate time series datasets that span various forecasting horizons. The results show that ForecastGAN consistently outperforms state-of-the-art transformer models for short-term forecasting while remaining competitive for long-term horizons. This research establishes a more generalizable approach to time series forecasting that adapts to specific contexts while maintaining strong performance across diverse data characteristics without extensive hyperparameter tuning.