A new method for decision-tree-based recommender systems is proposed. The proposed method includes two new major innovations. First, the decision tree produces lists of recommended items at its leaf nodes, instead of single items. This leads to reduced amount of search, when using the tree to compile a recommendation list for a user and consequently enables a scaling of the recommendation system. The second major contribution of the paper is the splitting method for constructing the decision tree. Splitting is based on a new criterion - the least probable intersection size. The new criterion computes the probability for getting the intersection for each potential split in a random split and selects the split that generates the least probable size of intersection. The proposed decision tree based recommendation system was evaluated on a large sample of the MovieLens dataset and is shown to outperform the quality of recommendations produced by the well known information gain splitting criterion.