Proto-oncogenes are a group of genes that cause normal cells to become cancerous as a result of mutations. Protooncogenes encode proteins that function to stimulate cell division, inhibit cell differentiation, and prevent cell death. While the identification of the proto-oncogene may occur at different phases of the cancer-causing processes, the accuracy of the identification method is always questionable. Prediction through in-vitro experimentations is considered sometimes a standard procedure but is very time taking, laborious, and costly. This problem is addressed by opting for computer-aided approaches established in bioinformatics and computational biology studies. Early prognosis of cancer is crucial towards the full recovery of the patient. Proto-oncogene proteins are an important biomarker that helps identify the onset of a specific type of cancer. Keeping this in mind, this study proposes an effective new method for the prediction of proto-oncogenes. The predictor proposed in this study calculates statistical moments and position-based features incorporated into pseudo amino-acid composition (PseAAC) based on Chou's 5step rules. Subsequently, the study proposes the use of a random forest classifier for the accurate prediction of proto-oncogenes. The method was validated using the 10 folds cross-validation, Jackknife testing, Self-Consistency, and Independent set testing, giving 95.44%, 94.89%, 97.38%, and 96.97% accurate results, respectively. These results depict that the proposed model can play a key role in the early prognosis of cancer and aid scientists in the discovery of mechanisms against cancer.