We build machine learning models for you which are capable of predicting future user behavior of your players.
We support you in developing and testing different strategies to dynamically adapt your game content.
With the help of artificial intelligence and machine learning, goedle.io analyzes player data to predict future behavior, provide meaningful insights, and help to adapt game content. These predictions and insights are used to identify interesting subgroups of players who can be engaged directly through goedle.io's dashboard. The engagement is not limited to user communication — our solutions go beyond this! Adapting the content dynamically based on the predictions is another use case and most often realized through our API. For example, we are currently supporting casual game studios to dynamically adjust the difficulty and helped to improve ad revenue by 74% after two weeks. Typical applications are:
Learn which players already have a hard time in your game and whom you can demand more from. Our algorithms help you to optimize the difficulty level in your game and can adapt it dynamically for each player individually. This maximizes the retention and increases the number of in-game purchases. Learn more »
Our algorithms learn when your players are likely to churn, so that you can proactively reach out to them. Combine this information with our engagement dashboard to decrease churn. Learn more »
Our algorithms also learn which players are more likely to purchase on their own and which players need some encouragement to do so. Use this information to offer vouchers or adapt pricing to increase the conversion rate and repeat sales. Learn more »
Recently, we faced the problem of creating unit tests for our Unity tracking SDK. The SDK enables game developers to transmit telemetric data to the goedle.io tracking API. To us, it is of great importance to ship reliable software. On the one hand, our customers have to trust our SDKs. On the other hand, if our SDKs or other components crash, we lose data and our algorithms only have access to incomplete data. Learn more »
Mobile games or educational apps are known to have plenty of data and the data itself already poses several interesting questions. For example, how do the level of difficulty and retention correlate? Once actionable insights have been gained from an analysis, machine learning helps to personalize the user experience to a level that exceeds human engagement options. E.g., adapting the difficulty for each user individually. Learn more »
We ran our churn prediction engine on data from NCSOFT's highly successful MMORPG Blade & Soul. NCSOFT is one of the largest MMO game developers in the world and not surprisingly, the Blade & Soul dataset contained hundreds of millions events. In our blog post, we share some hints and insights on predicting churn in this dataset. Learn more »
After more than two years in the mobile and web space, it is about time to add support for Unity to our data acquisition environment. We have recently received an increasing number of requests for a Unity integration so that we believe it is now the right time to support one of the industry-leading platforms for game development. Learn more »