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

2025/06/06 by Zhiyuan Zhao, Zhao, Zhiyuan, Juntong Ni +9 · 3 citations
Computer Science · Decision Sciences · Engineering · #FOS: Computer and information sciences #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Machine Learning in Healthcare #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2506.06482

openalex publication_date 2025/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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. To mitigate this gap, we propose TimeRecipe, a unified benchmarking framework that systematically evaluates time-series forecasting methods at the module level. TimeRecipe conducts over 10,000 experiments to assess the effectiveness of individual components across a diverse range of datasets, forecasting horizons, and task settings. Our results reveal that exhaustive exploration of the design space can yield models that outperform existing state-of-the-art methods and uncover meaningful intuitions linking specific design choices to forecasting scenarios. Furthermore, we release a practical toolkit within TimeRecipe that recommends suitable model architectures based on these empirical insights. The benchmark is available at: https://github.com/AdityaLab/TimeRecipe.

Citations

• Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
• U-Cast: Learning Hierarchical Structures for High-Dimensional Time Series Forecasting
• TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting
• How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook
• Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights
• TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation
• Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
• Context is Key: A Benchmark for Forecasting with Essential Textual Information
• TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis
• GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
• Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
• Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
• Unlocking the Power of LSTM for Long Term Time Series Forecasting
• Deep Time Series Models: A Comprehensive Survey and Benchmark
• Are Language Models Actually Useful for Time Series Forecasting?
• TSI-Bench: Benchmarking Time Series Imputation
• Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
• Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis
• TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
• TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
• Chronos: Learning the Language of Time Series
• LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting
• A decoder-only foundation model for time-series forecasting
• ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons
• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
• Performative Time-Series Forecasting
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
• AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecasting
• FITS: Modeling Time Series with 10k Parameters
• The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting
• Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
• TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
• Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures
• NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search
• Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting
• Are Transformers Effective for Time Series Forecasting?
• ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
• AutoFITS: Automatic Feature Engineering for Irregular Time Series
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• VEST: Automatic Feature Engineering for Forecasting
• Automated Model Selection for Time-Series Anomaly Detection
• Reformer: The Efficient Transformer
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
• NAS-Bench-101: Towards Reproducible Neural Architecture Search
• The M4 Competition: Results, findings, conclusion and way forward
• Attention Is All You Need
• DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
• Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
• TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting
• Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
• The M4 Competition: 100,000 time series and 61 forecasting methods
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Cited by

• An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers
• Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
• TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting

Related

• TSPP: A Unified Benchmarking Tool for Time-series Forecasting
• What Matters in Deep Learning for Time Series Forecasting?
• Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect
• SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series
• Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs