No abstract

Banks generally use credit scoring models to assess the creditworthiness of customers when they apply for loans or credit. These models perform significantly worse when used on potential new customers than existing customers, due to the lack of financial behavioral data for new bank customers. Access to such data could therefore increase banks’ profitability when recruiting new customers. If allowed by the customer, Open Banking APIs can provide access to balances and transactions from the past 90 days before the score date. In this study, we compare the performance of conventional application credit scoring models currently in use by a Norwegian bank with a deep learning model trained solely on transaction data available through Open Banking APIs. We evaluate the performance in terms of the AUC and Brier score and find that the models based on Open Banking data alone are surprisingly effective in predicting default compared to the conventional credit scoring models. Furthermore, an ensemble model trained on both traditional credit scoring data and features extracted from the deep learning model further outperforms the conventional application credit scoring model for new customers and narrows the performance gap between application credit scoring models for existing and new customers. Therefore, we argue that banks can increase their profitability by utilizing data available through Open Banking APIs when recruiting new customers.

Banks’ credit scoring models are required by financial authorities to be explainable. This paper proposes an explainable artificial intelligence (XAI) model for predicting credit default on a unique dataset of unsecured consumer loans provided by a Norwegian bank. We combined a LightGBM model with SHAP, which enables the interpretation of explanatory variables affecting the predictions. The LightGBM model clearly outperforms the bank’s actual credit scoring model (Logistic Regression). We found that the most important explanatory variables for predicting default in the LightGBM model are the volatility of utilized credit balance, remaining credit in percentage of total credit and the duration of the customer relationship. Our main contribution is the implementation of XAI methods in banking, exploring how these methods can be applied to improve the interpretability and reliability of state-of-the-art AI models. We also suggest a method for analyzing the potential economic value of an improved credit scoring model.

In this study, we examine the efficiency and unbiasedness of Atlantic salmon futures prices. Market participants use the Fish Pool futures market to hedge the increasingly volatile salmon spot price. We further examine the futures market's predictive accuracy, comparing it to a variety of proprietary prediction models. Our results show that futures prices are efficient and unbiased in the long‐run, while being biased and inefficient in the short‐run. Moreover, we find that futures prices provide an adequate price discovery function for most contracts, while suffering from magnified risk premiums due to few noncommercial traders.

In this study, we examine the credit risk of banking bonds. We apply two option-based credit default models originally derived by Merton and Black and Cox, with the aim of producing objective credit ratings and credit spreads. A credit rating process can never be purely objective and typically credit rating assessments are highly dependent on subjective judgment on the part of credit analysts. We do believe, however, that the credit rating industry might benefit from employing objective methods to help foster consistency in the rating processes (which some CRAs already do, e.g., Moody's). Employing data from two Norwegian banks, our analysis is designed to capture the characteristics of the Nordic financial bond market. The results indicate that structural models are well suited to computing plausible credit default probabilities, as well as credit spreads and to performing credible credit ratings of Nordic banks, given that the input parameters are properly estimated.