부산대학교 도서관

Due to the extensive and ever-growing collection of android apps, it has become quite difficult for users to find apps that they are truly interested in. When looking for android app, the user has a particular goal in mind and wishes to find an app that can truly meets their needs and expectations. App recommendation systems play a vital role in this regard by recommending apps to users based on their preference and requirements. The goal of this project was to develop a machine learning based app recommendation system to recommend Android Apps to the users. We collected the screenshots and metadata of a total of 12000 android apps, divided across ten different categories. CNN model architecture was trained on Vgg16 ImageNet weights. The model’s prediction was followed by Feature Extraction which was further used as a basis for Linear Regression to finally recommend an app of interest to the users.