Dear students,
As you might know, the ERCIS has a long-standing tradition of having Lunchtime Talks during the semester. Usually, they take place at Leo 18, but due to some specific circumstances, they will be held virtual this year. On November 17th, we will have the first talk – if you are interested, please register with the link below, and you will receive the Zoom link today by 11.45, afterwards in due time before.
https://www.ercis.org/research/ercis-lunchtime-seminar
About the talk:
We are pleased to invite you to the first talk in the series, presented by Dr. Johannes Kriebel. Johannes is an assistant professor at the Finance Center Münster. His work focuses on topics related to credit risk and machine learning as well as digital transformation in financial service providers.
Johannes will present a project on the use of natural language processing to predict credit risk from user-generated text data on peer-to-peer lending platforms. Please find an abstract, as well as further details for logging in, below.
We will open the waiting room at 12.00 (UTC+1) and open doors to the “seminar room” at 12.15. As usual, we will have time for discussions afterwards until roughly 13.00.
Abstract
Digital technologies produce vast amounts of unstructured data that can be stored and accessed by traditional banks and fintech companies. Existing literature on the topic indicates that certain aspects of this unstructured data can be valuable for decision-making regarding the acceptance and pricing of credit contracts. Both practitioners and academics are interested in understanding the value of this information and how to exploit it for credit risk predictions. We employ deep learning techniques to extract credit-relevant information from user-generated text on the peer-to-peer platform Lending Club. Our results confirm that even short pieces of user-generated text can improve credit default predictions significantly and generate substantial additional profit for lenders. We benchmark four deep neural network architectures and more traditional approaches (machine learning and rule-based text characteristics) to retrieving credit-relevant information from text. Average embedding neural networks, convolutional neural networks, and recurrent neural networks achieve similar prediction quality while outperforming convolutional recurrent neural networks. Deep learning models achieve better results than traditional approaches in almost all cases; in traditional approaches, spelling mistakes are particularly informative.
