MotoLease LLC improved the accuracy of its internal credit forecasting model called M-Score 2.0 last month by using machine learning techniques and alternative data, according to a document shared with Powersports Finance.
The company claims the new scoring model predicts consumer creditworthiness with 66.2% accuracy, compared with 63.5% accuracy for its previous version, called M-Score 1.0, and 60% accuracy for Fico scores.
M-Score 2.0 uses machine learning — a form of artificial intelligence that allows technology to learn without manual input — to “better predict performance of new lease originations using traditional and enriched alternative data,” according to the document.
