SciPlay uses machine learning for churn prevention and player personalization

Overview

SciPlay, a mobile social gaming company behind titles like Jackpot Party and Quick Hit Casino, built machine learning models with MLflow on the Databricks Data + AI Platform, including a churn prevention model that identifies players at risk of churning and customer segmentation models that target cohorts of players with personalized gaming experiences. This drove a 5% uplift in user retention across games, 75% faster time-to-market for new games and features, and reduced time-to-insight for nontechnical teams from 4 hours to 4 minutes (60x faster).

The challenge

SciPlay's cloud data warehouse was complex to manage and costly to scale as the company and its data grew exponentially; disconnected data silos blocked access to key information, made sharing across teams a struggle, and the company could take hours instead of minutes to make a critical decision.

The solution

With the Databricks Data + AI Platform, SciPlay unified behavioral, session and attribution data with analytics and AI, building machine learning models within MLflow including a churn prevention model to identify customers at risk of churning and customer segmentation models to target cohorts of players with personalized gaming experiences.

Reported business value

Since adding lakehouse to its tech stack, SciPlay has seen a 5% uplift in user retention across multiple games, can now launch new games an average of 75% faster than before, and non-data teams benefit from time-to-insight reduced from 4 hours to just 4 minutes, a 60x improvement.