mlsanityData to 14 Oct 2026

Forecast-Then-Optimize Deep Learning Methods

arXiv 2506.13036 ↗First posted 16 Jun 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Time series forecasting underpins vital decision-making across various sectors, yet raw predictions from sophisticated models often harbor systematic errors and biases. We examine the Forecast-Then-Optimize (FTO) framework, pioneering its systematic synopsis. Unlike conventional Predict-Then-Optimize (PTO) methods, FTO explicitly refines forecasts through optimization techniques such as ensemble methods, meta-learners, and uncertainty adjustments. Furthermore, deep learning and large language models have established superiority over traditional parametric forecasting models for most enterprise applications. This paper surveys significant advancements from 2016 to 2025, analyzing mainstream deep learning FTO architectures. Focusing on real-world applications in operations management, we demonstrate FTO's crucial role in enhancing predictive accuracy, robustness, and decision efficacy. Our study establishes foundational guidelines for future forecasting methodologies, bridging theory and operational practicality.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 69 of its 153 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

69 of 153 references.

References · 69

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  5. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  8. 2020Reformer: The Efficient Transformercited by 1,668
  9. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  10. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  11. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  12. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
38 more
  1. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  2. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  3. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  4. 2024Chronos: Learning the Language of Time Seriescited by 759
  5. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  6. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
  7. 2018Deep learning for time series classification: a reviewcited by 576
  8. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  9. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  10. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  11. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  12. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  13. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 332
  14. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
  15. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  16. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
  17. 2021Ensemble deep learning: A reviewcited by 284
  18. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
  19. 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variablescited by 248
  20. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  21. 2019Understanding and Improving Layer Normalizationcited by 217
  22. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  23. 2023FITS: Modeling Time Series with 10k Parameterscited by 195
  24. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 182
  25. 2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 180
  26. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 172
  27. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  28. 2021Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solutioncited by 157
  29. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  30. 2023Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictorscited by 113
  31. 2024Approaching Human-Level Forecasting with Language Modelscited by 107
  32. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 107
  33. 2024From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflectioncited by 98
  34. 2017Dilated Recurrent Neural Networkscited by 83
  35. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 76
  36. 2024Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretabilitycited by 70
  37. 2023DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Predictioncited by 49
  38. 2022Criteria for Classifying Forecasting Methodscited by 48

50 most cited of 69 All 69 (JSON)

Built on by

Not cited yet.