Systems | Development | Analytics | API | Testing

July 2020

Predicting 1st-Day Churn in Real-Time - MLOps Live #7 - With Product Madness (an Aristocrat co.)

Michael Leznik - Head of Data Science Matthieu Glotz - Data Scientist Yaron Haviv - CTO & Co-Founder We discuss how technology and new work processes can help the gaming and mobile app industries predict and mitigate 1st-day (or D0) user churn in real time — down to minutes and seconds using modern streaming data architectures such as KAPPA. Also, we explore feature engineering improvements to the RFM (Recency, Frequency, and Monetary) churn prediction framework: The Discrete Wavelet Transform (DWT).

Predicting 1st Day Churn in Real Time

Survival analysis is one of the most developed fields of statistical modeling, with many real-world applications. In the realm of mobile apps and games, retention is one of the initial focuses of the publisher once the app or game has been launched. And it remains a significant focus throughout most of the lifecycle of any endeavor.

Breaking the Silos Between Data Scientists, Engineers & DevOps with New MLOps Practices

Effectively bringing machine learning to production is one of the biggest challenges that data science teams today struggle with. As organizations embark on machine learning initiatives to derive value from their data and become more “AI-driven” or “data-driven”, it’s essential to find a faster and simpler way to productionize machine learning projects so that they can make business impact faster.