Financial Services
Egypt’s MNT-Halan uses AI credit scoring for underserved borrowers
The OECD highlighted Egypt’s MNT-Halan as an example of AI-based credit scoring using alternative data. The approach reportedly approved many applicants who lacked sufficient conventional credit histories.
An OECD report describes the use of AI-based credit scoring by Egypt’s MNT-Halan to assess applicants who lack sufficient conventional financial records. The model uses alternative data to reduce reliance on traditional credit histories and collateral.
The report says that around 60% of applicants previously considered “unscoreable” were reportedly approved through the model. This expands the pool of people who can potentially access formal financial products.
The application is particularly relevant to women entrepreneurs and other customers operating outside traditional banking channels. Digital finance, mobile wallets, payment cards, and formal accounts can help build financial histories that may support future borrowing.
The example illustrates how machine learning can be applied to financial inclusion rather than only to back-office automation. For lenders, alternative-data models can create new assessment methods; for customers, they may reduce barriers created by limited conventional documentation. [6]
Original source: OECD