Effective analysis of stress level using logistic regression compared with random forest
Tonmoy Roy Akash, U. Arul · 2025
The purpose of this research is to compare the efficacy of random forest and logistic regression in order to enhance stress level analysis through the use of supervised learning techniques. Two sets of participants in the study were given a dataset of 1,468 samples—1,144 for training and 533 for testing—to evaluate logistic regression on. In order to forecast fraudulent service websites, each group used a sample size of 10 N. While random forest obtained an accuracy of 85.236%, logistic regression was able to attain 94.448%. When it comes to identifying bogus applications, the logistic regression shows a statistically significant p-value of 0.002 (p<0.05). The results demonstrate that because logistic regression has a higher accuracy than random forest, it performs better in identifying fraudulent services.