Self-motivation and Academic Performance In Computer Programming Language Using a Hybridised Machine Learning Technique

The advancement in artificial intelligence (AI) and Machine learning (ML) have made it easier to foreknown feature happens from current and past trends. Once Self-efficacy and self-confidence are believed to be, an individual trait associated with academic brilliance. Using a hybridised Random Forest and Support Vector Machine (RFSVM) ML model we predicted students' academic performance in computer programming courses, based on their self-confidence, self-efficacy, positive thinking, focus, big goals, a motivating environment and demographic data. Benchmarking our RFSVM model against Decision Tree (DT) and K-Nearest Neighbour (K-NN) model, the RFSVM recorded and accuracy of 98% as against 95.45% for DT and 36.36% for K-NN. The error between actual values and predicted values of the RFSVM model was better (RMSE = 0.326401, MAE = 0.050909) and compared with the K-NN (RMSE = 2.671397, MAE = 1.954545) and DT models (RMSE = 0.426401, MAE = 0.090909). The results further revealed that students with a high level of self-confidence, self-efficacy and positive thinking performed well in computer programming courses