Statistical research based on data is one of the primary keys to the development of the world. But the size of the data is getting increased very rapidly. For this reason, statistical data analysis is getting complicated, and sometimes the existing data mining techniques are not providing significant and satisfactory results. On the other hand, traditional classification techniques provide results that are not statistically significant every time. In this research, a Mixture Decision Tree algorithm is being proposed that is a more powerful classification technique, and that may provide better results than the existing methods. In this Mixture Decision Tree, the Classification and Regression Tree (CART) algorithm is combined with k-means clustering, by which the primary data is filtered in two stages. Applying this method to some predefined data, significant enhancement is found in the classification precision for the current classification techniques. The Mixture Decision Tree algorithm is slightly more complex than the existing methods, but computer programming techniques can be done quickly.