This has created a huge shift in purchasing behavior among customers towards speed, convenience, reliability which was pioneered by the emergence of Q-commerce (Quick commerce). Given this rapidly evolving landscape, gaining insights into the key drivers of customer loyalty in this sector is critical for businesses to sustain a competitive advantage. With this study, it will be revealed that how ANN and Logistic Regression can serve the purpose of predicting the consumer behavior and loyalty in Q-commerce. This study employs modern predictive modeling techniques to analyze the factors that impact consumer loyalty in Q-commerce. A structured questionnaire was sent to 350 respondents who were actively using Q-commerce platform capturing their demographic and behavioral variables. The data were analyzed through IBM SPSS, utilizing ANN (Multi-layer Perceptron) and Logistic Regression to assess the connection between consumer behavior and loyalty. The independent variables were gender, satisfaction level, delivery time importance, ease of use and Q-commcence usage while the dependent variable is loyalty. The ANN model showed excellent predictive power, and the Logistic Regression identified that satisfaction level and ease of use were statistically significant variables to predict the loyalty. Classification accuracy was measured and model performance was assessed using Receiver Operating Characteristic (ROC) curve. These findings are particularly valuable for Q-commerce businesses to improve customer experience, tailor marketing, and reduce customer churn. This study lays the groundwork for research on consumer behavior in Q-commerce by combining machine learning approaches, making both practical and theoretical contributions.