Aim: To enhance the accuracy in predicting covid cases using Novel linear regression over support vector machines (SVM). Materials and Methods: Two groups were used in this research. Group 1 is Linear regression also used for regression and classification. Group 2 is Support vector machine is a supervised machine learning algorithm that can be used for both the classification and regression challengers. Accuracy rate of classifiers is measured using covid-19 symptom dataset to assess their performance. Required samples for analysis were calculated using G power calculation and Pretest Power is found to be 25%. Result: The result proved that novel linear regression with better accuracy than SVM. The linear regression is significantly better than SVM. The two groups linear regression (Group 1) with 97.57% has more mean accuracy than SVM (Group 2) with 95.35% and attained the significance value of p = 0.03 (p<0.05). In the table datasets are prepared using 10 as sample size for linear regression and SVM. Conclusion: The results have proved that linear regression helps in predicting covid cases and gives more accuracy for covid prediction than SVM, with enhanced accuracy.