The classification of Gender and Ethnicity has been utilized in diverse scenarios, specifically in the realm of human-computer interaction, visual surveillance, and electronic customer services. Predicting the gender and ethnicity of individuals presents a significant obstacle due to its complex characteristics. The escalating prevalence of social media has emphasized the utmost importance of independently predicting gender and race. In this research endeavor, a framework is utilized which utilizes a Convolutional Neural Network to forecast gender and ethnicity by utilizing various outputs starting from the initial stage. The model’s performance was evaluated using different metrics, including the F1-score, accuracy, precision, recall, and accuracy. The methodology is evaluated using the UTKFace dataset for predicting gender and ethnicity, and compared the model with previous study to understand which model is giving better accuracy.