Predicting creditworthiness in retail banking with limited scoring data

Abstract

The preoccupation with modelling credit scoring systems including their relevance to predicting and decision making in the financial sector has been with developed countries, whilst developing countries have been largely neglected. The focus of our investigation is on the Cameroonian banking sector with implications for fellow members of the Banque des Etats de L'Afrique Centrale (BEAC) family which apply the same system. We apply logistic regression (LR), Classification and Regression Tree (CART) and Cascade Correlation Neural Network (CCNN) in building our knowledge-based scoring models. To compare various models' performances, we use ROC curves and Gini coefficients as evaluation criteria and the Kolmogorov-Smirnov curve as a robustness test. The results demonstrate that an improvement in terms of predicting power from 15.69% default cases under the current system, to 7.68% based on the best scoring model, namely CCNN can be achieved. The predictive capabilities of all models are rated as at least very good using the Gini coefficient; and rated excellent using the ROC curve for CCNN. Our robustness test confirmed these results. It should be emphasised that in terms of prediction rate, CCNN is superior to the other techniques investigated in this paper. Also, a sensitivity analysis of the variables identifies previous occupation, borrower's account functioning, guarantees, other loans and monthly expenses as key variables in the forecasting and decision making processes which are at the heart of overall credit policy.

FinBrain: when finance meets AI 2.0

“…Meanwhile, AI technology combined with big data can help build robust credit systems, assess business risks under uncertainty, and achieve anti-fraud functions. For example, diversified data sources can be utilized to build a credit system based on the tree model (Yeh, Lin et al 2012), neural network (Khashman 2010, Abdou, Tsafack et al 2016, and support vector machine model (Han, Han et al 2013). Moreover, businesses rely increasingly on AI technology for competitive advantages, and IoT provides risk managers abundant information for assessing and managing risks.…”

Prediction of financial strength ratings using machine learning and conventional techniques

“…As per the information value 6 score, 'Size' is the most influential non-financial predictor with a sore of 3.139. 'Sovereign Country Risk Rating' (SR) with an information value score of 2.712 comes second.…”

“…'Sovereign Country Risk Rating' (SR) with an information value score of 2.712 comes second. 6 Information value directly relates to a statistical technique called Weight of Evidence (WoE) which identifies the strength of different predictor indicators, as an alternative to Chi2. For more details the reader is referred to Abdou et al (2016).…”

Development and Usage of Scoring Systems in Giving Mortgages by Commercial Banks of Latvia

“…A framework for developing causal credit default theories is introduced through the example of a new residential mortgage default theory (Wilson, 2007). Table 4 presents information developed by a group of researchers (Abdou et al, 2016) about the nature of the loan, the personal characteristics of the borrower and the borrower's history.…”