TsSHAP: Robust model agnostic feature-based explainability for time series forecasting

03/22/2023
by   Vikas C. Raykar, et al.
0

A trustworthy machine learning model should be accurate as well as explainable. Understanding why a model makes a certain decision defines the notion of explainability. While various flavors of explainability have been well-studied in supervised learning paradigms like classification and regression, literature on explainability for time series forecasting is relatively scarce. In this paper, we propose a feature-based explainability algorithm, TsSHAP, that can explain the forecast of any black-box forecasting model. The method is agnostic of the forecasting model and can provide explanations for a forecast in terms of interpretable features defined by the user a prior. The explanations are in terms of the SHAP values obtained by applying the TreeSHAP algorithm on a surrogate model that learns a mapping between the interpretable feature space and the forecast of the black-box model. Moreover, we formalize the notion of local, semi-local, and global explanations in the context of time series forecasting, which can be useful in several scenarios. We validate the efficacy and robustness of TsSHAP through extensive experiments on multiple datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/17/2021

TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models

Time series forecasting is a demanding task ranging from weather to fail...
research
04/06/2021

Towards a Rigorous Evaluation of Explainability for Multivariate Time Series

Machine learning-based systems are rapidly gaining popularity and in-lin...
research
11/02/2020

A Learning Theoretic Perspective on Local Explainability

In this paper, we explore connections between interpretable machine lear...
research
09/28/2022

Explainable classification of astronomical uncertain time series

Exploring the expansion history of the universe, understanding its evolu...
research
06/29/2018

Posthoc Interpretability of Learning to Rank Models using Secondary Training Data

Predictive models are omnipresent in automated and assisted decision mak...
research
07/21/2021

GLIME: A new graphical methodology for interpretable model-agnostic explanations

Explainable artificial intelligence (XAI) is an emerging new domain in w...
research
09/06/2022

Making the black-box brighter: interpreting machine learning algorithm for forecasting drilling accidents

We present an approach for interpreting a black-box alarming system for ...

Please sign up or login with your details

Forgot password? Click here to reset