Mobile game maker keeps big spenders engaged
Use Case
Churn, upsell, lifetime value
Industry: Mobile games
The Game: In the 20 top-grossing games in category with over 5M downloads
Solution: Identify potential VIP, high-value players to increase retention and in-game spend
Platform Use Case: Churn, upsell, lifetime value
Data Stack: BigQuery
3x
prospected VIPs
2x
lower churn rate
3.5x
uplift of spend per user
Challenge
Keeping and enticing gamers
A mobile game maker wanted to start using predictive analytics for in-game management and to assess its business performance and bottom-line impact. They focused on one of their games, ranked in the 20 top-grossing games in its category with over 5M downloads, to see if results could be further boosted by applying AIArtificial intelligence (AI) refers to the development of computerized systems that can carry out tasks and perform actions that augment or take the place of….
Like any online company, this game maker wanted to identify its customers, build distinct profiles for each, and match them with appropriate offers and content. Prior to using Pecan, the company managed only to partially leverage its data to improve business results, despite boasting many unique active players a week and engaging in hundreds of thousands of weekly transactions.
This game maker also faced the common problem of player churn. Finally, they also had difficulty in adapting their offerings to different player profiles and found it hard to identify high-value players early enough in their relationship with the game.
Solution
A predictive approach
Before turning to Pecan, this gaming company used manual statistical methods to build distinct profiles and match each of the profiles with appropriate marketing offers, content, and products.
The results were less than optimal, so the company used Pecan to build 3 predictive analyticsPredictive analytics uses data, statistics, and machine learning techniques to build mathematical models that can generate predictions about things likely to happen in the future…. models, each focused on a specific predictionA prediction is the ultimate goal of a predictive model. In Pecan, a prediction is often tied to a specific customer. After learning from data… task:
- Identify potential high rollers
- Predict which of these customers is receptive to marketing activities
- Predict which of these customers will churn
This type of data-driven segmentation ensures that players are continuously getting value from the game. Informing personalized marketing outreach with these predictions can increase revenues, reduce churn, and help build successful future products.
This company built the three models with Pecan in 12 days. That’s a dramatic improvement on the 4-6 months typically required for traditional, manually executed solutions to these challenges.
It’s also important to note that one of the customer’s BIBusiness intelligence (BI) includes gathering, storing, and analyzing business data, as well as using that analysis to inform the actions of the business. managers built these AI models using the Pecan platform. Using Pecan avoided the need to involve data scientists, who are often overloaded with demands from various teams and can be difficult to access for projects like these.
Because the BI manager was able to use Pecan and achieve solid predictive models in such a short amount of time without data scienceData science combines statistics, computer science, scientific methods, and business knowledge to analyze, model, and predict using data. The data science toolkit can be used… resources, the project cost was estimated to be just 25% the cost of alternative solutions.
Results
Owning the future
The Pecan modelIn the context of machine learning, a model is a specific instance or example of an algorithm that has been created based on a particular… identified more than 200% additional potential “high rollers” or VIP players. By treating those potential VIPs with special care early in their lifecycle, the company converted the majority of them into highly valuable customers. Each segment was tested separately, and the average segment saw 3X uplift of spend per user.
With the users who were predicted to churn, similar tests showed equally strong results:
- Users who weren’t provided customized offers did actually churn
- Pecan’s identification of those likely to churn helped cut churn in half
- Users who received customized offers spent more than 4X more than those who didn’t
This mobile gaming company determined the results of this campaign: less churn with higher spent per user and, most critically, a small investment of time and resources for a fast ROI.
The company quickly reaped the rewards of empowering its BI team with the capability of building state-of-the-art AI predictive analyticsAnalytics is a business practice that uses descriptive and visualization techniques to gain insight into data; those insights can then be used to guide business… models. The results reveal the powerful benefits of adopting a predictive approach to users’ future behavior and taking action based on that foresight.
Contents
It’s time to refine your outreach with customer foresight
Latest Resources
10 Data Breakthroughs That Solve Business Problems
Are you curious about your enterprise and how you can improve your business? Meet our latest Data Science breakthroughs.
Predictive Analytics: Getting Actual Value from Machine Learning
In this webinar, we shared the essential components of predictive analytics to get value in the shortest time possible.
Stop User Churn in 3 Steps with Predictions
In a constant battle for user time, developers need to keep their users engaged and happy while monitoring reduced engagement and churn rates.