# Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting

**Authors:** Bryan Lim, Sercan O. Arik, Nicolas Loeff, Tomas Pfister  
**arXiv:** [1912.09363](https://arxiv.org/abs/1912.09363)  
**Date:** 2019-12-19  
**Summary page:** https://www.summarizepaper.com/en/paper/1912.09363v1/

## Key points

- The paper addresses the challenge of multi-horizon forecasting problems that involve a complex mix of inputs.
- Deep learning models for multi-step prediction often lack interpretability and do not account for the full range of inputs present in common scenarios.
- The authors introduce the Temporal Fusion Transformer (TFT), an attention-based architecture that combines high-performance multi-horizon forecasting with interpretable insights into temporal dynamics.
- The TFT utilizes recurrent layers for local processing and interpretable self-attention layers to learn long-term dependencies at different scales.
- The model also includes specialized components for selecting relevant features and gating layers to suppress unnecessary components, enabling high performance in a wide range of regimes while providing practical interpretability use cases.
- The authors demonstrate significant performance improvements over existing benchmarks on various real-world datasets using TFT.
- Three practical interpretability use cases of TFT are showcased: feature importance analysis, anomaly detection, and counterfactual analysis.
- Overall, this paper presents a novel approach to multi-horizon time series forecasting that combines high accuracy with interpretability and has potential applications in various domains such as finance, healthcare, and transportation.

## Summary

The paper "Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting" by Bryan Lim, Sercan O. Arik, Nicolas Loeff, and Tomas Pfister addresses the challenge of multi-horizon forecasting problems that involve a complex mix of inputs, including static covariates, known future inputs, and exogenous time series observed historically without prior information on how they interact with the target. While deep learning models have been proposed for multi-step prediction, they often lack interpretability and do not account for the full range of inputs present in common scenarios. To address these issues, the authors introduce the Temporal Fusion Transformer (TFT), an attention-based architecture that combines high-performance multi-horizon forecasting with interpretable insights into temporal dynamics. The TFT utilizes recurrent layers for local processing and interpretable self-attention layers to learn long-term dependencies at different scales. The model also includes specialized components for selecting relevant features and gating layers to suppress unnecessary components. This enables high performance in a wide range of regimes while providing practical interpretability use cases. The authors demonstrate significant performance improvements over existing benchmarks on various real-world datasets using TFT. They showcase three practical interpretability use cases of TFT: feature importance analysis, anomaly detection, and counterfactual analysis. Overall, this paper presents a novel approach to multi-horizon time series forecasting that combines high accuracy with interpretability and has potential applications in various domains such as finance, healthcare, and transportation.