Analysis of Apps in the Google Play Store
Android is the dominant mobile operating system today with about 85% of all mobile devices running Google’s OS. The Google Play Store is the largest and most popular Android app store.
The purpose of our project was to gather and analyze detailed information on apps in the Google Play Store in order to provide insights on app features and the current state of the Android app market.
We collected descriptive information on over 3,100 apps across 11 different categories in the Google App Store. We focused on the following 11 categories: Business, Food & Drink, Books & Reference, Travel & Local, Health & Fitness, News & Magazines, Education, Social, Finance, Medical, and Entertainment.
Each app has its own web page where detailed information about the app is available. We used Selenium to scrape information about each of these apps for our analysis. We scraped app title, category, developer name, whether an app contains ads, rating, number of reviews, app size, number of installs, and price.
Exhibit 1: Scraping the Google Play Store
Health & Fitness, Travel & Local and Education were the most common categories, accounting for about 15%, 14% and 13%, respectively, of the total number of apps in our dataset. Food & Drink was the least prevalent category with only 87 observations (less than 1% of the total number of apps in our dataset). Four categories of applications, including Health & Fitness, Travel & Local, Education and Finance, accounted for more than 50% of the apps in our dataset.
Exhibit 2: Number of Apps Available for Download by Category
Most of the apps (58%) in the Google Play Store were free to install at the time of data collection. However, 26% of free apps had in-app purchases feature, concealing their true cost. In-app purchasing refers to buying extra content or subscriptions inside an application on a mobile device. Free apps are more likely to have in-app purchases feature.
Exhibit 3: Free vs. Paid Apps
In general, advertising is the most popular app monetization model. Indeed, more than 5o% of free apps in our dataset were supported by advertising in contrast to the paid apps, among which less than 1% featured ads.
Exhibit 4: Advertising
It looks like certain app categories have more free apps available for download than others. In our dataset, the majority of apps in Food & Drink, News and Magazines, as well as Social categories were free to install. At the same time, Health & Fitness, Travel & Local, Education, and Medical categories had the biggest number of paid apps available for download.
Exhibit 5: Free and Paid Apps by Category
The Google Play Store offers a wide range of applications, but most of these apps had been downloaded only by a small number of people. In our dataset, 28% of the apps had been downloaded fewer than 100 times, and about 74% of the apps had been downloaded fewer than 50K times. Among the apps that had been downloaded between 500M to 1B+ times were Instagram, Facebook, Google + and Google News.
Exhibit 6: Number of Installs
An average rating of 4.4 (out of 5.0) is the most common rating in our dataset. Specifically, 266 apps out of 3,144 apps are rated with an average rating of 4.4. Most of the apps (74%) are rated within the range of 4.8 to 3.8.
Exhibit 7: Distribution of User Ratings
It looks like only a small number of users take the time to write an app review. On average, somewhere between 3% and 8% of users who download an app write reviews in the Google Play Store. Our analysis has shown that users tend to leave more reviews for apps in finance, health & fitness, and business categories.
Exhibit 8: Number of Reviews as Percent of Downloads
The boxplot below provides more details on the distribution of user reviews. Median number of reviews as percent of downloads is about 2.5%, with a range from as little as 0.03% to almost 10%.
Exhibit 9: Number of Reviews as Percent of Installs
Most of the paid apps in the Google Play Store are inexpensive. The majority of apps cost about $1. The average price of all paid applications in our dataset is about $6.9. App prices range from $0.99 to $399.99.
Exhibit 10: Distribution of App Prices
Counter-intuitively, $2-3 apps and $4-6 apps have more aggregated downloads than cheaper apps, which are below $2. Expensive apps, which are above $30, are less popular, and there are also fewer of these apps available for download in the Google Play Store.
Exhibit 11: Aggregated Downloads of Paid Apps
The Google Play Store shows apps’ actual download sizes. In 2015, Google increased the app size limit allowed on the Google Play from 50MB to 100MB, and in 2016 it started displaying apps’ true download sizes.
Average app’s download size in our dataset is 17.3MB, with a range between 0.02MB and 100MB. Education and Travel & Local app categories have the highest average download size, while Finance category is the smallest on average.
Exhibit 12: Average Download Size by Category
We found that there is no correlation between app features like size, rating, number of installs and price. Surprisingly, it appears that there is no correlation between price and rating as well as between rating and whether an app contains ads or not.
Exhibit 13: Correlations
Exhibit 14: Correlation Between Rating and Price
The chart below shows the number of unique developers in each category. Health & Fitness, Education and Finance are the most popular categories among developers.
Exhibit 15: Number of App Developers by Category
The majority of app developers build apps only in one category (2,251). Only a small number of developers build apps associated with two or more categories. For instance, only 34 developers made apps for two categories, 6 developers built apps for 3 categories and 2 developers built apps for 4 categories. Only one developer built apps for 8 categories and, not surprisingly, that developer was Google LLC.
Exhibit 16: Number of App Developers by Contribution to Each Category