This paper discusses the problem of loan portfolio in fuzzy random environment, in real life, because of the influence of random and fuzzy factors, the return rates of loan in bank often have fuzzy random characteristic. Mean chance is a measure of fuzzy random variable, based on mean chance, a new optimization model of loan portfolio is provided. To give a general solution to the new model, a hybrid intelligent algorithm is designed. The algorithm integrates fuzzy random simulation, neural network and genetic algorithm. Neural network is employed to calculate the expected value and the mean chance value, it greatly reduce the computational work. At last, a numerical example is presented to illustrate the new model and the proposed new algorithm.