Efficient Student Performance Prediction in Online Education During Covid using Novel Inception Compared over Xception with Improved Accuracy

Instead of the less reliable Exception, we want to utilize Novel Inception to predict how well COVID-19 online course participants will do. As a whole, this research focuses on two algorithms: Exception and Novel Inception. Each category will be surveyed with twenty persons. A significant result for the dataset was produced using SPSS with a G-power value set at 85%. They are also compared using different sample sizes to see how accurate they are. With a prediction accuracy of 96.0100% for online class performance during COVID, the state-of-the-art Inception algorithm decisively defeats the Exception method. When evaluating how well the two groups performed in enhancing the precision of online student education, the Exception algorithm combined the Novel Inception method stood out with a p-value of 0.000 (p<0.05). The Novel Inception algorithm outperforms the Exception method when it comes to forecasting how well students will do in their COVID online classes.