Fit evaluation plays an important role in garment products development and sales. Effective clothing fit evaluation methods can reduce the development cost of apparel products and the return rate of online apparel sales. In this research, we proposed an intelligent fit evaluation technology to predict clothing fit. The mathematical relationship model between clothing fit levels and indexes reflecting the clothing fit levels was constructed by using decision tree C4.5 algorithm. Then, two experiments were carried out to collect input and output training data. After learning from the collected data, the proposed model can predict clothing fit accurately. Next, we validated our proposed model’s prediction accuracy using K-fold cross validation. Finally, we gave two applications of the proposed model for clothing products development and shopping online. Results show that our proposed method has high prediction accuracy and less requirement for the number of learning samples, and can predict clothing fit automatically and rapidly without real try-on.