IrelandFinance and insurance2023 – ongoingWayflyer
Machine-learning enrichment of bank transactions for underwriting
Ntropy reported that Wayflyer's merchant-identification accuracy rose from below 30% to around 80%
Problem
Wayflyer needed to interpret bank transactions when assessing ecommerce borrowers. Inconsistent data from open-banking providers limited its internal classification models as lending expanded internationally.
Approach
Wayflyer integrated Ntropy's transaction-enrichment API into its underwriting workflow. The service identified merchants and categorised spending, replacing work that Wayflyer had attempted with internal models.
Results
Takeaway
The reported accuracy improvement concerned merchant identification and enrichment. It did not establish an improvement in loan performance.
Categories
- Industry
- Finance and insurance
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Evidence
- Vendor case study
Sources
Source summaries
Ntropy described Wayflyer's replacement of internal enrichment models with its API. It reported merchant-identification and enrichment accuracy rising from below 30% to around 80%.
Full details are in the original sources.
