Covid-19 pandemic has ignited an unprecedented risk for the economy. Banks and financial institutions across the globe are expected to register unusually high default rates on loans once the moratorium and forbearance imposed by the governments and the regulators are lifted.
Scientific tools such as collection and recovery scorecards offer a mechanism to predict defaults on the loan portfolio and also suggest appropriate actions to alleviate debt collection and recovery risk. In this webinar video, learn how you can use machine learning to develop collection scorecards to improve debt collection efficiency. Also, learn how to implement collection scorecards to reduce bad debts on your portfolio.
Machine Learning is not only used to reduce loan defaults but it can also be used to increase debt collections and recoveries.
That’s correct, Christine.
AI isn’t simply used to decrease credit defaults however it can likewise be utilized to build delinquent payment assortments and recuperations.
Hello Rupam ji,
Amazing webinar. Thank you.
I have a question here. If you are intending to build a collection score card for a lets say digital lending product such as buy now pay later model of digital lending, but the product has not gone live and there is no data collection, then can we build a collection score card in the form of a reference model using credit card and non-collateralized personal loans?
Appreciate you response.
Hi. In case it is a new product then using scorecards for similar products as a proxy is a reasonable approximation. In this case, it is recommended to monitor the collection performance closely and modify the scorecard based on new evidence/data.
First of all, I loved your video ,found your video very useful. I am trying to build ML powered scorecard for short term(15-30 days tenure) loan app . Is there any github repo where i can look for code for your above video ?
Hi Rahul, there is no GitHub code repository for this webinar however I suggest this risk scoring case studies which you will find useful