This competition focuses on PAYGo SHS contracts data.
When a customer applies for a loan, banks and other credit providers use statistical models to determine whether or not to grant the loan based on the likelihood of the loan being repaid. The factors involved in determining this likelihood are complex, and extensive statistical analysis and modelling are required to predict the outcome for each individual case. You must implement a similar model that predicts PAYGo SHS contract repayments or defaults based on the data provided.
In this competition, you must explore and cleanse a dataset consisting of over ~37000 PAYGo SHS contracts to determine the best way to predict the repayment profile. You must then build a machine learning model that returns the expected future payments for n months ahead (for this competition n=6).
You could empower your solution by predicting the contract repayment status label (a probability of being paid or not paid) as well. This could indicate whether the contract will be fully paid or defaulted.
Files available for download: