The goal of this paper is to jointly model the development of individual daim payments and daims incurred. Our analysis only focuses on the development of the so-called Reported But Not Settled (RBNS) daims. We develop regression models and postulate distributions which we can be used in practice to fully describe the joint development process of individual daim payments and daims incurred. We apply neural networks to estimate our regression models. As regressors we use the whole daims history of incremental payments and daims incurred, as well as any feature information which is available to describe individual daims and their development characteristics. The fit of our regression models and postulated distributions is validated in a practical example on real data set.