# Explainable time-series forecasting with sampling-free SHAP for Transformers

arXiv: https://arxiv.org/abs/2512.20514 · HTML: https://mlsanity.com/paper/2512.20514/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 76 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [True to the Model or True to the Data?](https://mlsanity.com/paper/2006.16234/) (2020)
- [AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers](https://mlsanity.com/paper/2402.05602/) (2024)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [Shapley explainability on the data manifold](https://mlsanity.com/paper/2006.01272/) (2020)
- [TimeSHAP: Explaining Recurrent Models through Sequence Perturbations](https://mlsanity.com/paper/2012.00073/) (2020)
- [Forecasting: theory and practice](https://mlsanity.com/paper/2012.03854/) (2020)
- [AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation](https://mlsanity.com/paper/2301.08110/) (2023)
- [WindowSHAP: An Efficient Framework for Explaining Time-series Classifiers based on Shapley Values](https://mlsanity.com/paper/2211.06507/) (2022)
- [Review of Low Voltage Load Forecasting: Methods, Applications, and Recommendations](https://mlsanity.com/paper/2106.00006/) (2021)
- [Open Power System Data - Frictionless data for electricity system modelling](https://mlsanity.com/paper/1812.10405/) (2018)
- [Short-Term Electricity Load Forecasting Using the Temporal Fusion Transformer: Effect of Grid Hierarchies and Data Sources](https://mlsanity.com/paper/2305.10559/) (2023)
- [A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI](https://mlsanity.com/paper/2307.05104/) (2023)
- [A Systematic Review for Transformer-based Long-term Series Forecasting](https://mlsanity.com/paper/2310.20218/) (2023)

## Built on by (most cited first, 2 of 2)

- [Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models](https://mlsanity.com/paper/2604.28149/) (2026)
- [FETS Benchmark: Foundation Models Enable Scalable and Generalizable Energy Time Series Forecasting](https://mlsanity.com/paper/2604.22328/) (2026)

## Abstract (arXiv)

Time-series forecasts are essential for planning and decision-making in many domains. Explainability is key to building user trust and meeting transparency requirements. Shapley Additive Explanations (SHAP) is a popular explainable AI framework, but it lacks efficient implementations for time series and often assumes feature independence when sampling counterfactuals. We introduce SHAPformer, an accurate, fast and sampling-free explainable time-series forecasting model based on the Transformer architecture. It leverages attention manipulation to make predictions based on feature subsets. SHAPformer generates explanations in under one second, several orders of magnitude faster than the SHAP Permutation Explainer. On synthetic data with ground truth explanations, SHAPformer provides explanations that are true to the data. Applied to real-world electrical load data, it achieves competitive predictive performance and delivers meaningful local and global insights, such as identifying the past load as the key predictor and revealing a distinct model behavior during the Christmas period.