Forecasting Obesity and Customized Nutrition Planning using KNN and Linear Regression Models for Higher Accuracy

This study deals with the various contributors of obesity through the use of advanced ML algorithms are KNN and linear regression. These KNN and linear regression algorithms help to ascertain the accuracy for a dataset through proper analysis of patterns and relationships within the data. This research gives custom-tailored diet plans for people found to be developing obesity. With G=0.8, alpha=0.05, and beta=0.2 the G-power tool helped to ascertain the sample size, therefore producing a total of 20 participants. On average, Linear Regression and K-Nearest Neighbors (KNN) are expected to be performing similarly. The algorithm predicted the data accurately within ±2 standard deviations. Results: The KNN algorithm reached 67% accuracy, while the other one that stood out, Linear Regression, with an accuracy of 89.26%. Findings: This study revealed that the Linear Regression algorithm was more accurate than the K-Nearest Neighbor method in predicting individual obesity levels.