CATS-Linear: Classification Auxiliary Linear Model for Time Series Forecasting
This work addresses the underexplored area of improving linear models in time series forecasting, offering a novel method that is incremental but provides strong performance gains for practitioners in fields like finance or climate prediction.
The paper tackles the problem of enhancing linear models for time series forecasting by proposing CATS-Linear, which uses classification to route instances to dedicated predictors and redesigns decomposition architectures, achieving state-of-the-art accuracy comparable to tuned baselines with fixed hyperparameters.
Recent research demonstrates that linear models achieve forecasting performance competitive with complex architectures, yet methodologies for enhancing linear models remain underexplored. Motivated by the hypothesis that distinct time series instances may follow heterogeneous linear mappings, we propose the Classification Auxiliary Trend-Seasonal Decoupling Linear Model CATS-Linear, employing Classification Auxiliary Channel-Independence (CACI). CACI dynamically routes instances to dedicated predictors via classification, enabling supervised channel design. We further analyze the theoretical expected risks of different channel settings. Additionally, we redesign the trend-seasonal decomposition architecture by adding a decoupling -- linear mapping -- recoupling framework for trend components and complex-domain linear projections for seasonal components. Extensive experiments validate that CATS-Linear with fixed hyperparameters achieves state-of-the-art accuracy comparable to hyperparameter-tuned baselines while delivering SOTA accuracy against fixed-hyperparameter counterparts.