Active Players is located under the Predictive Player Insights group from the System Dashboards in the Data Studio. You can navigate to it by;
Insights & Analytics menu - Data Studio - Dashboards - System Dashboards - Predictive Player Insights - Active players.
Note: The Probability of Return data model is calculated using three variables; First Deposit Date, Last Deposit Date & Deposit Count.
Based on these three criteria, the model predicts a players' state of engagement
If you want to read more about our Predictive Churn Prevention Model, you can do so here.
Here's a quick reminder of our predictive segments and scores;
- Sky-High - Score is above 83.5%
- High - Score is between 67% and 83.5%
- Medium - Score is between 50.5% and 67%
- Low - Score is between 34% and 50.5%
- Frail - Score is between 17.5% and 34%
- Critical - Score is between 10% and 17.5%
- Dead - Score is less than 10% (Inactive)
The Active Player Dashboard displays some key metrics to give you an insight into your player engagement. Looking at the example below we can see some important information at our disposal.
Let's take a look at each metric in more detail;
Total Players - This refers to the total number of players who are eligible to be part of the Probability of Return model. To be eligible to be part of the model, players need to have deposited on two different days.
In This Example: 19,238 players have made at least two deposits over at least two days and are therefore included in the Probability of Return segmentation.
Engaged - This refers to all those players, within the Total Players, who fall into the active segments (Sky-High, High, Medium, Low, Frail or Critical) are classified as engaged.
In This Example: We have 12,372 players who belong to Sky-High, High, Medium, Low, Frail or Critical segments.
Inactives - Inactives refer to all players, within the Total Players, who fall into the Inactive / Lost / Dead segment. In other words, any player who does not belong to the engaged group of players.
In This Example: We have 6,866 players who belong to the Inactive segment.
Average Deposited Per Player: Here we can see the average amount deposited, per player, in your base currency. This is the total deposits of the total players, divided by the total number of players which gives us the Average Deposit Amount Per Player.
In This Example: The average amount deposited per player is €1,544
Here you can drill down into more detail between each of the predictive segments;
- How many players belong in each segment?
- How have the players moved between the segments from yesterday to today?
- How many players are currently active?
- Which players run a high risk of churning right now?
We present this information in the Yesterday versus Today Segment matrix. This matrix documents the player movements and the segment the player belonged to yesterday versus the segment the player belongs to today. This information is calculated on a daily basis.
When you see the count of players in a segment, you can click to reveal the full list of the players and download their data.
Understanding the Matrix:
In this example (image above)
- 6814 players were inactive yesterday and remain inactive today
- 78 player was Sky-High yesterday and Inactive today
- 52 players were Inactive yesterday and Critical today 🙌
We have added tables that present some principal financial KPIs per segment. You can find information about the players' deposits and withdrawals. To compare their value, we have added average deposits per player for each segment.
The model calculates new scores for players every 24 hours. At that time, the segmentation also gets updated. By default, both get updated at 05:00:00 UTC.
Need freshly-updated segmentation at another time of day, for example, right before you run your campaigns? Do not hesitate to discuss the options with your Partner Manager.
You have now seen how engaged your players currently are. To take things to the next level, we can look at how to add more value by retaining your players for longer. We explain how to build automated Churn Prevention using the Predictive model here: