The recent mortgage crisis has resulted in several bank failures. Under the current Basel I capital framework, banks are not required to hold a sufficient amount of capital to support the risk associated with their mortgage activities. The new Basel II capital rules are intended to be more risk based and would require the right amount of capital buffer to support bank risk. However, Basel II models could become too complex and too costly to implement, often resulting in a trade-off between complexity and model accuracy. Since the Basel II rules are meant to be principal based (rather than prescriptive), banks have the flexibility to build risk models that best fit their unique structure. We find that the variation of the model, particularly how mortgage portfolios are segmented, could have a significant impact on the default and loss estimated. This paper finds that the calculated Basel II capital varies considerably across the default prediction model and segmentation schemes, thus providing banks with an incentive to choose an approach that results in the least required capital for them. We find that a more granular segmentation model produces smaller required capital, regardless of the economic environment. Our results suggest that banks may have incentives to build risk models that meet the Basel II requirement and still yield the least amount of required capital.