This study aims to provide actionable insights for Android app developers seeking to improve the installation rates and ratings of their applications on the Google Play Store. The dataset used in this study was sourced from Kaggle. Our analysis focuses on identifying key factors that contribute to the success and marketability of Android applications.
Specifically, we examine the impact of variables such as app category, review volume, app size, pricing model (free or paid), recency of updates (measured as the number of months since the last update), and required Android version. Additionally, we provide insights into critical aspects like the number of reviews, overall ratings, and app category, which are essential for developers looking to optimize their apps for the market. To analyze these factors, we employ both supervised learning techniques (including regression and decision tree models) and unsupervised learning methods (such as association rule mining), with the goal of uncovering patterns that can guide the development of successful and marketable applications for the Google Play Store.
Class Group project at CMU
December 2019