South KoreaFinance and insurance2019 – ongoingHanwha General Insurance
Alpha Underwriting insurance assessment
Hanwha General Insurance reported at least 95% agreement between Alpha Underwriting and human assessors
Problem
Underwriters had to review and approve applications individually, including those involving minor illnesses or accidents. Applicants waited while those checks were completed.
Approach
Hanwha developed Alpha Underwriting using machine learning. The system supplied predicted underwriting decisions with explanations. Development began in 2019, and the initial rollout covered simplified-underwriting and driver insurance.
Results
Takeaway
The agreement figure came from simplified-underwriting insurance. It did not establish performance across every product the insurer planned to cover.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
Asia Times reported Hanwha's introduction of its internally developed underwriting system. Hanwha reported at least 95% agreement with human decisions after training with more than 500 variables in simplified-underwriting insurance.
Full details are in the original sources.