Prediction of Depression using the KNeighbors-Classifier Algorithm Compared for Improved Accuracy with Support Vector Machine

The intention of the research is to regulate the level of precision via comparing the Support_Vector_Machine(S-V-M) algorithm and KNeighbors Classifier for predicting Depression. The proposed machine learning method aims to enhance the accuracy of depression prediction using the S-V-M algorithm, in evaluation with the Novel KNeighbors Classifier. The training dataset comprises two groups, with 10 individuals in each group. The example size calculation conducted via a pretest control of 80%, a significance level of 0.05%, then a 95% sureness interval. When associated to the current system, which has an accurateness of only 84%, it remained originate that the future method attained 95% accuracy. Here exists no consequence amid the S-V-M Model then KNeighbors Classifier Prototypical grounded on a example T-test through the p value is 0.000 (p<0.050). next it indicates that There exists a statistically meaningful distinction between the outcomes of the two algorithms. The outcomes of the training indicate that the KNeighborsClassifier procedure has a higher accurateness in predicting depression compared to the existing system. While the current system is capable of predicting depression, the Novel KNeighbors Classifier algorithm exhibits better performance in depression prediction. Therefore, the Novel KNeighbors Classifier algorithm is recommended for depression prediction.