Beyond Relevance: Factor-level Causal Explanation for User Travel Decisions with Counterfactual Data Augmentation.

Autor: Li, Hanzhe, Gu, Jingjing, Lu, Xinjiang, Shen, Dazhong, Liu, Yuting, Deng, YaNan, Shi, Guoliang, Xiong, Hui
Zdroj: ACM Transactions on Information Systems; Sep2024, Vol. 42 Issue 5, p1-31, 31p
Abstrakt: The article focuses on understanding users' Point-of-Interest (POI) choices in urban travel scenarios, which is complicated due to various influencing factors and data sparsity issues leading to misinterpretations. Introducing a Factor-level Causal Explanation framework (FCE-UTD), the study proposes a method to distinguish true causal factors from spurious ones using counterfactual data augmentation.
Databáze: Complementary Index