This paper addresses the issue of the induction of orthogonal, oblique and mul­tivariate decision trees. Algorithms pro­posed by other researchers use heuristic, usually based on the information gain con­cept, to induce decision trees greedily. These algorithms are often tailored for a given tree type ( e.g orthogonal), not be­ing able to induce other types of decision trees. Our work presents an alternative way. We propase to induce a decision trees ( without regarding the type) with an uni­fied algorithm based on artificial evolution. Experiments were performed with GALE, our fine-grained parallel Evolutionary Al­gorithm, and another well-known induc­tion technique on several datasets. Re­sults suggest that Evolutionary Algorithms are competitive and robust for inducing ali kinds of decision trees, achieving sorne­times better performance than traditional approaches.