The construction project is managed by construction managers who familiar with the project management knowledge areas. These construction managers know everything intelligent means discerning or looking around and well informed by their professions. However, in the world especially in low income countries particularly in Ethiopia, the majority of construction projects in construction companies fail due to a lack of construction project managers who are unfamiliar with the contract management that are used without considering the company's situations and project contexts. This study aims to develop a prediction model using machine-learning approach for identifying effective contract type in construction enterprises. Purposive sampling method is used to data from Amhara National Regional State Job & Training Bureau and their branches namely addis zemen, woreta and Debretabor Construction enterprise construction associations. The experimental results on the testing data set results a performance accuracy of SVM 92.58%, DT 92.30%, NB 91.48%, KNN 91.20% and LR 82.14% respectively. Moreover, from the experimental results, SVM outperformed the best as compared to the other classifiers. The study recommends predicting the effective contract type by collecting more construction project datasets from construction companies using deep learning approaches to compare with our results.