Analyze the Lack of Accuracy in Stock Price Prediction using Novel K-Nearest Neighbors Regression Compared with Logistic Regression to Improve Accuracy

This article's main goal is to make Novel K-Nearest Neighbors Regression more accurate at stock price prediction than the method for logistic regression. By employing the Novel KNN and LR methods, the analysis is carried out with a sample size of n = 10 and a G power of 80%. The information was gathered from several web sources, with a threshold of 0.05 percent, a confidence range of 95%, and a standard error of the mean and mean. When compared to the logistic regression technique, the novel K-Nearest Neighbors Regression has a high accuracy of 70.53 percent (49.52 percent). There is no statistically significant difference between the research groups with p = 0.840 and p > 0.05. For the stock price prediction of a customer, it shows that the novel KNN Regression appears to generate more accuracy than the LR algorithm..