The quick implementation of e-learning systems produces concerns about whether men and women experience different outcomes when learning through these systems. A research study analyzes gender variations in digital proficiency and perceptive evaluations of e-learning technology through machine learning pattern detection which uses primary survey information. The Decision Tree model evaluated unseen patterns between genders in the data. The research demonstrated that male participants achieved better accuracy results (76.47%) than female participants (74.07%). Studies showed that male respondents achieved absolute category classification accuracy (1.000) yet their category detection rate amounted to (0.600) whereas female respondents demonstrated steady precision-recall ratios throughout all classes. The research showed that male participants demonstrated excellent precision abilities in particular situations but female participants maintained a consistent precision rate in all categories. E-learning interventions require gender-specific design approaches according to the study to improve both adoption rates and outcome achievements. Future studies should evaluate various social and cultural elements together with analyzing additional demographic groups to enhance digital education adoption initiatives.