South KoreaPublic sector2024 – ongoingKorea Expressway Corporation
AI route prediction for toll-debt enforcement
Korea Expressway reported toll-enforcement hit rates rising from about 25% to 90% after AI route prediction
Problem
Enforcement teams estimated where toll debtors would leave the highway and often waited without finding them. Unpaid tolls continued to accumulate.
Approach
Korea Expressway introduced AI route prediction in June 2024. The system analyzed habitual routes and travel times, then texted teams a likely exit and arrival time when a debtor entered the highway. Officers intercepted vehicles and collected payment.
Results
Takeaway
Better interception rates did not establish that total unpaid tolls fell. Officers still handled pursuit and collection.
Categories
- Size
- Large enterprise
- Industry
- Public sector
- Business function
- Finance, risk and legalProduction and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
ChosunBiz accompanied enforcement officers and described the operational prediction system. It relayed a hit-rate increase from about 25% to 90%, alongside rising collections and continuing growth in unpaid tolls.
Full details are in the original sources.