Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.15950 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917784658640896 |
|---|---|
| author | Ma, Hongnan McAreavey, Kevin Liu, Weiru |
| author_facet | Ma, Hongnan McAreavey, Kevin Liu, Weiru |
| contents | Time series forecasting, while vital in various applications, often employs complex models that are difficult for humans to understand. Effective explainable AI techniques are crucial to bridging the gap between model predictions and user understanding. This paper presents a framework - TSFeatLIME, extending TSLIME, tailored specifically for explaining univariate time series forecasting. TSFeatLIME integrates an auxiliary feature into the surrogate model and considers the pairwise Euclidean distances between the queried time series and the generated samples to improve the fidelity of the surrogate models. However, the usefulness of such explanations for human beings remains an open question. We address this by conducting a user study with 160 participants through two interactive interfaces, aiming to measure how individuals from different backgrounds can simulate or predict model output changes in the treatment group and control group. Our results show that the surrogate model under the TSFeatLIME framework is able to better simulate the behaviour of the black-box considering distance, without sacrificing accuracy. In addition, the user study suggests that the explanations were significantly more effective for participants without a computer science background. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15950 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TSFeatLIME: An Online User Study in Enhancing Explainability in Univariate Time Series Forecasting Ma, Hongnan McAreavey, Kevin Liu, Weiru Artificial Intelligence Time series forecasting, while vital in various applications, often employs complex models that are difficult for humans to understand. Effective explainable AI techniques are crucial to bridging the gap between model predictions and user understanding. This paper presents a framework - TSFeatLIME, extending TSLIME, tailored specifically for explaining univariate time series forecasting. TSFeatLIME integrates an auxiliary feature into the surrogate model and considers the pairwise Euclidean distances between the queried time series and the generated samples to improve the fidelity of the surrogate models. However, the usefulness of such explanations for human beings remains an open question. We address this by conducting a user study with 160 participants through two interactive interfaces, aiming to measure how individuals from different backgrounds can simulate or predict model output changes in the treatment group and control group. Our results show that the surrogate model under the TSFeatLIME framework is able to better simulate the behaviour of the black-box considering distance, without sacrificing accuracy. In addition, the user study suggests that the explanations were significantly more effective for participants without a computer science background. |
| title | TSFeatLIME: An Online User Study in Enhancing Explainability in Univariate Time Series Forecasting |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2409.15950 |