AI-BASED PERSONALIZED MOBILE APP RECOMMENDATIONS USING CROWDSOURCED EDUCATIONAL DATA

Abstract

The rapid growth of mobile applications has created a need for intelligent recommendation systems that help users discover relevant and useful apps. Traditional mobile app recommendation methods often rely on user ratings, download counts, or simple collaborative filtering techniques, which may not fully capture users’ educational needs and preferences. To address this limitation, this study proposes an AI-based personalized mobile app recommendation system that leverages crowdsourced educational data. The proposed framework collects and analyzes crowdsourced information such as user feedback, learning outcomes, usage patterns, and educational relevance of mobile applications. Machine Learning and Deep Learning algorithms are applied to process this large-scale data and identify patterns that reflect user interests and learning objectives. By integrating collaborative filtering, content-based filtering, and deep learning models, the system generates personalized recommendations tailored to individual users. The proposed approach improves recommendation accuracy by incorporating real-world educational insights gathered from the crowd, enabling the system to better understand the effectiveness and relevance of mobile applications in educational contexts. Experimental results demonstrate that the AI-driven recommendation model provides more relevant, adaptive, and personalized suggestions compared to traditional recommendation systems. This system can assist students, educators, and lifelong learners in discovering suitable educational applications, thereby enhancing the overall mobile learning experience and promoting effective digital education.