TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness

ArXi:2506.06482v3 Announce Type: replace Time-series forecasting is an essential task with wide real-world applications across domains. While recent advances in deep learning have enabled time-series forecasting models with accurate predictions, there remains considerable debate over which architectures and design components, such as series decomposition or normalization, are most effective under varying conditions. Existing benchmarks primarily evaluate models at a high level, offering limited insight into why certain designs work better.