Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate Models
This paper focuses on explaining changes over time in globally sourced annual temporal data with the specific objective of identifying features in black-box models that contribute to these temporal shifts. Leveraging local explanations, a part of explainable machine learning/XAI, can yield explanati...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/4/626 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849719690769727488 |
|---|---|
| author | Shou Nakano Yang Liu |
| author_facet | Shou Nakano Yang Liu |
| author_sort | Shou Nakano |
| collection | DOAJ |
| description | This paper focuses on explaining changes over time in globally sourced annual temporal data with the specific objective of identifying features in black-box models that contribute to these temporal shifts. Leveraging local explanations, a part of explainable machine learning/XAI, can yield explanations behind a country’s growth or downfall after making economic or social decisions. We employ a Local Interpretable Model-Agnostic Explanation (LIME) to shed light on national happiness indices, economic freedom, and population metrics, spanning variable time frames. Acknowledging the presence of missing values, we employ three imputation approaches to generate robust multivariate temporal datasets apt for LIME’s input requirements. Our methodology’s efficacy is substantiated through a series of empirical evaluations involving multiple datasets. These evaluations include comparative analyses against random feature selection, correlation with real-world events as explained using LIME, and validation through Individual Conditional Expectation (ICE) plots, a state-of-the-art technique proficient in feature importance detection. |
| format | Article |
| id | doaj-art-b60fdb4684f94d2aba701209b7391375 |
| institution | DOAJ |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-b60fdb4684f94d2aba701209b73913752025-08-20T03:12:05ZengMDPI AGMathematics2227-73902025-02-0113462610.3390/math13040626Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate ModelsShou Nakano0Yang Liu1Physics and Computer Science, Wilfrid Laurier University, Waterloo, ON N2L 3C5, CanadaPhysics and Computer Science, Wilfrid Laurier University, Waterloo, ON N2L 3C5, CanadaThis paper focuses on explaining changes over time in globally sourced annual temporal data with the specific objective of identifying features in black-box models that contribute to these temporal shifts. Leveraging local explanations, a part of explainable machine learning/XAI, can yield explanations behind a country’s growth or downfall after making economic or social decisions. We employ a Local Interpretable Model-Agnostic Explanation (LIME) to shed light on national happiness indices, economic freedom, and population metrics, spanning variable time frames. Acknowledging the presence of missing values, we employ three imputation approaches to generate robust multivariate temporal datasets apt for LIME’s input requirements. Our methodology’s efficacy is substantiated through a series of empirical evaluations involving multiple datasets. These evaluations include comparative analyses against random feature selection, correlation with real-world events as explained using LIME, and validation through Individual Conditional Expectation (ICE) plots, a state-of-the-art technique proficient in feature importance detection.https://www.mdpi.com/2227-7390/13/4/626artificial intelligenceFLAMLimputationLocal Interpretable Model-Agnostic Explanationmachine learningXAI |
| spellingShingle | Shou Nakano Yang Liu Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate Models Mathematics artificial intelligence FLAML imputation Local Interpretable Model-Agnostic Explanation machine learning XAI |
| title | Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate Models |
| title_full | Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate Models |
| title_fullStr | Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate Models |
| title_full_unstemmed | Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate Models |
| title_short | Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate Models |
| title_sort | interpreting temporal shifts in global annual data using local surrogate models |
| topic | artificial intelligence FLAML imputation Local Interpretable Model-Agnostic Explanation machine learning XAI |
| url | https://www.mdpi.com/2227-7390/13/4/626 |
| work_keys_str_mv | AT shounakano interpretingtemporalshiftsinglobalannualdatausinglocalsurrogatemodels AT yangliu interpretingtemporalshiftsinglobalannualdatausinglocalsurrogatemodels |