Google Playstore Application Analysis and Prediction

Abstract

Application distribution platform, for example, Google play store gets overwhelmed with a few thousands of new applications regularly with a lot progressively a huge number of designers working freely or on the other hand in a group to make them successful. With the enormous challenge from everywhere throughout the globe, it is basic for a developer to know whether he is continuing the correct way. Dissimilar to making movies where the nearness of famous heroes raise the likelihood of accomplishment even before the movies are coming into the picture, it isn't the situation with creating applications. Since most Play Store applications are free, the income model is very obscure and inaccessible regarding how the in-application buys, in-application adverts and memberships add to the achievement of an application. In this way, an application's prosperity is normally dictated by the quantity of installation of the application and the client appraisals that it has gotten over its lifetime instead of the income is created. So in this project, I have tried to perform analysis and prediction into the Google Play store application dataset that I have collected from kaggle.com. Using Big Data techniques such as Hive I have tried to discover the relationships among various attributes present in my dataset such as which application is free or paid, about the user reviews, rating of the application. And using Deep Learning I have tried to make a prediction about the user reviews that which review is positive or negative.