Predicting mortgage default using convolutional neural networks

Publication details

Journal: Expert Systems With Applications, vol. 102, p. 207–217, 2018
Publisher: Elsevier
International Standard Numbers:
- Printed: 0957-4174
- Electronic: 1873-6793
Links:
- ARKIV: http://hdl.handle.net/10852/71665
- FULLTEKST: http://publications.nr.no/1552287038/MortgageDefaultKvamme18.pdf
- DOI: doi.org/10.1016/j.eswa.2018.02.029

We predict mortgage default by applying convolutional neural networks to consumer transaction data. For each consumer we have the balances of the checking account, savings account, and the credit card, in addition to the daily number of transactions on the checking account, and amount transferred into the checking account. With no other information about each consumer we are able to achieve a ROC AUC of 0.918 for the networks, and 0.926 for the networks in combination with a random forests classifier.