ShraddhaRajcoomar13/african-credit-scoring-challenge

Develop a robust ML model to predict loan default probability for diverse African markets, incorporating local economic & demographic factors; top 10 winners also create a scalable credit scoring function by binning risk probabilities into actionable categories. # african-credit-scoring-challenge Financial institutions need to predict loan defaults to mitigate risk and optimise lending decisions. In Africa’s rapidly growing financial markets, with diverse customer demographics and dynamic economic conditions, accurately assessing default risk is more important than ever. In this challenge, we want you to develop a robust, generalisable machine learning model to predict the likelihood of loan defaults for both existing customers and new applicants. Beyond accurate predictions, we encourage yous to innovate by incorporating unique factors relevant to each financial market. The objective of this challenge is to develop a machine learning model that accurately predicts the probability of loan default. The top 10 winners, in addition to submitting their solution, will need to design and submit a credit scoring function, using their model's outputs and probabilities. This step involves binning model outputs into risk categories and proposing a scalable credit risk score. By accurately predicting loan defaults, your work will enable the client organisation to create a credit scoring solution to evaluate risk more effectively, improving decisionmaking, reducing financial losses associated with high-risk lending, and allowing for expansion into new financial markets. The challenge provider is a private asset manager that operates in several financial markets across Africa. zindi.africa