App Download Estimates Explained by our Data Scientists

As pioneers of the app store marketing industry, AppTweak has accumulated 10+ years of app store data (we’re talking hundreds of millions of data points) from an extensive range of categories and countries.

Leveraging this huge pool of data, our data scientists have built an algorithm that can estimate the downloads and revenue of any app in the App Store and Google Play.

Read below to learn more about our data scientists’ methodology and how we compute the most accurate app download and revenue estimates at AppTweak, using insights taken directly from AppTweak’s Market Intelligence.

What factors influence app downloads?

Before we dig into the data science, we wanted to remind you of the two major elements that are closely related to mobile app downloads: category ranking and seasonality.

App downloads and category rank

The first is an app’s category ranking. Back in 2020, we found a very close correlation between an app’s ranking in its category and its daily downloads. Typically, the number of downloads an app gets in one day has a direct impact on its category rank for several days.

Of course, each category has its own level of competition. For example, the top 10 apps in the Games category typically drive many more downloads each day compared to the top 10 Tools apps. We see this huge difference when comparing total downloads and revenues over time on both the App Store and Google Play below.

This is also true from a country perspective. For instance, the US is by far the most competitive country on the App Store, while India takes the lead on Google Play. In practice, games will require more daily downloads to rank in the top positions in these countries compared to any others.

Having developed a deep-learning model for download and revenue estimates based on 10+ years of app store data, our data scientists have therefore managed to calculate the competitiveness of each category and country, estimating the number of daily downloads an app needs to reach the top charts of a specific country and category.

App downloads and seasonality

Another element that influences the downloads an app drives is seasonality. Seasonal events can have a huge impact on mobile app downloads. Below are a couple of examples to illustrate this.

AppTweak was chosen as Phiture’s preferred app data provider. Learn why in this blog

Apps in the sports industry tend to see downloads fluctuate around popular sports events in different countries. For instance, in the US we see an increase in downloads of up to +51% in September when the NFL season starts. On the other hand, in India we see peaks of up to 50% in April during the Indian Premier League.

If we compare the yearly trend of the travel category across countries, we also see that download trends are quite different from one hemisphere to another.

In the US and UK, travel apps tend to see downloads increase during their summer (between June and September). On the other hand, travel apps in Brazil observe a similar increase in traffic during their summer (between October and January).

Other seasonality effects can be seen throughout the week. Below are a couple of examples of app categories that see different download trends on weekdays vs. weekends.

Unsurprisingly, mobile games tend to drive more downloads during weekends, whereas business apps drive more during the week.

Another example is one of sports vs. health & fitness apps. They also follow quite different trends; the former typically drives more downloads during the weekend while the latter receives a peak in traffic at the start of the week.

More on our market seasonality feature

Using deep learning to enhance our data science estimates

To better understand the data science behind these numbers, we asked our Head of Data Science, Jonathan Frisch, to explain the methodology and algorithms used by the team:

As a pioneer in the app store marketing field, it was a priority for us to use deep learning to estimate the number of downloads an app drives every day in any store and country on iPhone, iPad, and Android.

One of the major advantages of using deep learning is producing a model that is both (1) cross-country and (2) cross-category. This means the model truly learns and understands the relationships between countries and categories, and can therefore benefit from the data of different categories in different parts of the world to estimate the overall downloads of one specific app.

Want to learn more about our unique data science? Read this blog on Atlas AI

For each device and app type, we feed our deep-learning model with the data collected from the thousands of apps connected to AppTweak. For each app – and every day – we define a set of features related to:

1. The app’s category rank
2. The date (seasonality)
3. The country

Then, we map these features to the number of daily downloads the app is driving, allowing our model to learn the most relevant relationships between the different features and their related downloads.

This technique helps us identify unique insights such as the impact of Christmas across different categories and countries, or which countries have similar levels of competitiveness in terms of downloads.

Learn more about app seasonality trends for the holiday season

Once our model has a deep understanding of these relationships, we are ready to predict the number of downloads for any app for which we don’t have data – from any category, in any country, and at any point in the past. Thanks to the many metrics we tracked during the learning process, we are confident that this model can estimate the downloads of an app with extremely high accuracy.

Specific examples of how our estimates perform

Our algorithms capture the effect of seasonality and specific events

By using deep learning algorithms, we can better capture the impact of seasonality and specific events on app downloads. For instance, events such as the COVID-19 lockdown in 2020 or the Christmas holidays might only impact specific apps in some specific countries. Our model is able to capture the impact of such events on app downloads at a very granular level, and only when and where relevant.

For example, if we look at a set of apps whose activity is affected by the Christmas holidays in a country where Christmas has a high seasonal impact, we will understand that the app ranking at #1 on December 25th will drive many more downloads than the app ranking #1 on November 25th in the same category.

We compared the Top Charts of the Entertainment category in the UK; apps in this category and country generally receive more downloads around Christmas. Below, we see that TikTok ranked in 3rd position on both November 25 and December 25, 2023.

However, when we look at TikTok’s daily downloads, we estimate that they are considerably higher in December.

Another example is the case of the COVID lockdown in Q2 2020. Below are 2 examples of apps that were heavily affected by the lockdown in the US. The first is the travel app TripAdvisor, which saw its daily downloads plunge during the lockdown. The second is the business app Zoom, which saw its downloads increase over the same period.

Estimates based on a large data pool

As mentioned above, our ability to provide our users with accurate download and revenue estimates is a result of the large pool of mobile app data we have captured over the years.

Our model uses the data from apps worldwide to predict estimates in each specific country. Typically, to predict the number of downloads a financial app makes in Vietnam, the model benefits not only from all the data we have access to in Vietnam but also from the data we have for any financial app in the world.

As our pool of data grows significantly over the years as more and more users connect their data to AppTweak, this data is fed into our algorithms which are constantly improved over time.

Key takeaways

1. App downloads and category rank are closely related. The rank of an app in its category indicates the level of daily downloads the app is driving. Of course, each category and country has its own level of competitiveness to consider.
2. Seasonality and specific events can significantly affect app downloads. Their impact depends on various elements such as the type of app, the country, and the event itself. These subtleties are captured by our estimates model.
3. Our model uses a huge pool of mobile data that has been accumulated over the past 10+ years. This dataset grows with AppTweak, which results in a higher level of accuracy for our estimates.

Explore accurate download estimates for apps on the App Store and Google Play with AppTweak

Start free trial