Identifying policy-relevant traffic crash risk factors in Cheongju, South Korea using logistic regression and explainable machine learning
Eun-Ji Lee, Sua Kim, Hyun-Ji Lee, Jae-Hwan Jhong · 2026
Read Identifying policy-relevant traffic crash risk factors in Cheongju, South Korea using logistic regression and explainable machine learning by Eun-Ji Lee, Sua Kim, Hyun-Ji Lee, Jae-Hwan Jhong (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0350616.txt.
Description
Eun-Ji Lee and colleagues mined police crash records from Cheongju, a mid-sized South Korean city, to find which factors turn a crash severe. They ran the same data through classical logistic regression and through four machine learning models with explanation tools, trusting only the risk factors both families agreed on. Policy, not prediction alone, was the goal.
Three culprits topped both approaches: running signals, neglecting safe-driving duties, and missing median barriers on undivided roads. Because the methods converge, officials can act with more confidence than a single model would justify. The study is a template as much as a result: pairing an old statistical workhorse with explainable machine learning gives cities findings that are both modern and defensible in a council meeting.
Catalog record
| CREATOR | Eun-Ji Lee, Sua Kim, Hyun-Ji Lee, Jae-Hwan Jhong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52819 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |