STUDY ON THE IMPACT OF PERSONALIZED RECOMMENDATIONS AND ADVERTISEMENTS BY FOOD DELIVERY APPLICATIONS USING MACHINE LEARNING: A CASE STUDY OF KHARGHAR

ABSTRACT The research investigates the impact of personalized recommendations and advertisements in food delivery applications, leveraging machine learning algorithms, within the urban setting of Kharghar, Maharashtra. Through a descriptive research approach involving a sample of 100 diverse users, the study aims to comprehensively explore various dimensions. Its objectives include assessing user perceptions, understanding the relationship between exposure to personalized recommendations and subsequent purchasing behavior, examining privacy concerns, evaluating recommendation relevance, and quantifying the effectiveness of machine learning techniques. The findings reveal that a significant majority of Kharghar users frequently encounter personalized recommendations and engage in purchasing activities facilitated by these applications. A statistically significant association is observed between exposure to recommendations and purchasing behavior, highlighting their pivotal role. However, the study uncovers a divergence in user sentiments, with some expressing satisfaction while others harbor concerns regarding accuracy and data privacy, underscoring the need for transparency and educational initiatives. Rejecting the null hypothesis strengthens the argument that personalized recommendations significantly influence purchasing behavior. Proposed recommendations include enhancing transparency, addressing privacy concerns, implementing educational initiatives, refining recommendation algorithms, and developing mechanisms for monitoring user behavior. These suggestions aim to empower users with greater trust and confidence in the application while optimizing the efficacy of personalized recommendations. In conclusion, the study emphasizes the critical role of personalized features in shaping user behavior and underscores the imperative for transparency and user education to foster trust and enhance user experiences in food delivery applications. Keywords- Online Food Delivery Applications, Personalized Recommendations, Food Delivery Applications, Machine Learning Algorithms, Purchasing behavior