The road construction industry has adopted information technology in the working process in terms of computer-assisted design and drafting, documentation, and performance evaluation. Identifying factors affecting the performance of road construction projects have become necessary to improve performance of the road construction industry. Which needs a dynamic and advanced analytic tool to organize and analyze data in construction management to obtain quick analysis and decision supporting results. We use data mining techniques and RStudio tools to build a model and analyze factors affecting the performance of Amhara rural road construction agency (ARRCA) projects. In this study, we use classification algorithms decision tree J48, Support Vector Machine (SVM), and Naïve Bayes (NB) and RStudio tools to build a model that classifies and predicts their severity. Compare the performance in the model building process based on precision, recall, Kappa statistics, and accuracy. In our study using, a 10-fold cross-validation test option was used to check the accuracy of each classifier. J48, SVM and NB, classifiers accuracy is 92.8%,88.5% and 86.2% respectively. J48 classifier has better classification accuracy than SVM and NB as its result indicates. The most determinant factors identified as it has shown from information gain analysis Improper planning and scheduling, Inaccurate contract quantity, Financial problem, and Design Change are serious problems requiring attention to be taken to minimize or control factors influencing performance road construction projects by concerned bodies. Finally, the finding of this study could be a reference document for experts, decision-makers, and researchers who are interested in the field.