Software risk prediction is the most sensitive and crucial activity of the SDLC. It may lead to the success or failure of the project. The requirement gathering stage is the most important and challenging stage of the SDLC. The risks should be tackled at this stage and saved to be used in future projects. However, a model is proposed for the prediction of software requirement risks using the requirement risk dataset and ML classification. This research study proposed a model for risk prediction in software requirements that will be evaluated using several evaluation measures (e.g., precision, F-measure, MCC, recall, and accuracy). For the completion of this study, the dataset is taken from Zenodo repository. The model is evaluated using ML techniques. After the finding and analysis of results, DT shows best performance with accuracy of 99%.