By: Bart Baesens, Seppe vanden Broucke
This QA first appeared in Data Science Briefings, the DataMiningApps newsletter. Also want to submit your question? Just Tweet us @DataMiningApps. Want to remain anonymous? Then send us a direct message and we’ll keep all your details private. Subscribe now for free if you want to be the first to receive our articles and stay up to data on data science news, or follow us @DataMiningApps.
You asked: I noted your work “Big Data For Credit Scoring: Adding Value using Mobile Phone Data and Social Network Analytics”, (Óskarsdóttir et al., 2018). It looks really interesting. Can you elaborate a bit further?
Our answer:
In recent years, a multitude of sophisticated classification techniques have been developed to improve the statistical performance of credit scoring models. Together with our newly graduated PhD, dr. Óskarsdóttir , in this research, instead of focusing on the techniques themselves, we leverage alternative data sources to enhance both statistical and economic model performance. We demonstrate how including call networks as a new Big Data source has added value in terms of both profit and statistical power. Using a unique combination of data sets, including call-detail records, credit and debit account information of customers, we create scorecards for credit card applicants. We use call-detail data to build call networks from which we extract features representing calling behavior of customers. Furthermore, we apply advanced social network analytics techniques where we propagate influence from prior defaulters throughout the network to inspect the effect known defaulters have on others and include this influence when building scorecards. Obviously, the usage of call detail record data for credit scoring raises some important ethical and privacy concerns which we also address.
