Summary of Tsfeatlime: An Online User Study in Enhancing Explainability in Univariate Time Series Forecasting, by Hongnan Ma et al.
TSFeatLIME: An Online User Study in Enhancing Explainability in Univariate Time Series Forecasting
by Hongnan Ma, Kevin McAreavey, Weiru Liu
First submitted to arxiv on: 24 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a new framework called TSFeatLIME for explaining univariate time series forecasting models. The framework integrates an auxiliary feature into the surrogate model and uses pairwise Euclidean distances to improve its fidelity. The authors conduct a user study with 160 participants to evaluate the effectiveness of these explanations, finding that they were more effective for individuals without a computer science background. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand time series forecasting better by creating a way to explain complex models in simpler terms. The researchers created a new framework called TSFeatLIME that makes it easier to see how forecast models work. They tested this framework with 160 people from different backgrounds, and found that the explanations were most helpful for those without a computer science background. |
Keywords
» Artificial intelligence » Time series
