Arrears management is the process by which loan accounts that have defaulted on their contractual repayments are managed. Although computational intelligence approaches such as artificial neural networks have been applied to the related field of loan approval/credit-scoring, there is little evidence of their application to arrears management. This thesis investigates the feasibility of using artificial neural networks to predict the risk of personal loan accounts falling into arrears. The data used is real live personal loan data sourced from a medium-sized Australian financial institution. The results are very encouraging, particularly those obtained when an ensemble rather than individual networks were used. The results also suggested that there is scope for further substantial research in this area.

Данное издание не является оригинальным. Книга печатается по технологии принт-он-деманд после получения заказа.