The introduction of 5G networks has created a pressing need for efficient spectrum sharing between 5G and Digital Video Broadcasting Satellite Second Generation systems in C-Band. Interference prevention is crucial to ensure a reliable coexistence. This study presents an ensemble-based machine learning approach that uses the majority vote strategy to predict interference between 5G and DVB-S2 systems, leveraging system parameters and environmental factors. The ensemble-based approach harnessed the voting strategy Random Forest, Support Vector Machines, Artificial Neural Networks, K-Nearest Neighbors, and Ridge Classifiers, for an informed decision. The comparative analysis of the ensemble-based approach against each classifier showed accuracy of 99.96%, 98.68%, 96.05%, 86.67, 96.05 and 82.89% for Ensemble, KNN, ANN, RF, Ridge, and SVM classifier respectively. The ensemble approach shows that the ensemble base model produces the best prediction model suitable for predicting the interference between 5G and DVB-S2. The research contributes to the development of efficient spectrum-sharing strategies, ensuring seamless coexistence of 5G and DVB-S2 systems in C-Band.