Presented By O'Reilly and Cloudera
Make Data Work
22–23 May 2017: Training
23–25 May 2017: Tutorials & Conference
London, UK

"Smartifying" the game

Iñaki Puigdollers (Social Point)
14:5515:35 Thursday, 25 May 2017
Level: Intermediate
Average rating: ****.
(4.00, 1 rating)

Who is this presentation for?

  • Product and business people, data scientists, and data analysts

Prerequisite knowledge

  • A basic understanding of business metrics, such as lifetime value (LTV) and average revenue per user (ARPU), and classification models (useful but not required)

What you'll learn

  • Learn how Social Point benefited from its own analytics department in creating a personalized experience for its users that translates to higher revenue at very low cost


Over the last year, Social Point has been working hard on developing its analytics features (also known in other industries as data products). In essence, analytics features are those features of the game that are tailor-made for users, created from the data Social Point already has about them. The result: a very big impact for both the game and the business itself—all at a very low cost.

Iñaki Puigdollers explores how the analytics department changed Social Point games, covering the models applied (what), the purpose of developing those models (why), and the impact that they had on its games (how much).

Topics include:

  • Dynamic balancing of Dragon Land (a platform game): A model that adapted the difficulty of the game based on your skill as player.
  • Early nonpayer prediction: Predicting whether you are going to pay or not (during your lifetime in the game) enables Social Point to offer you the tools you may need to make your gaming experience more enjoyable.
  • Churn prevention campaign: Predicting whether a player is going to churn or not enables Social Point to offer them what they need to keep enjoying the game.
Photo of Iñaki Puigdollers

Iñaki Puigdollers

Social Point

Iñaki Puigdollers is a data scientist at Social Point, where he leads the analytics function in the biggest game of the company (Dragon City). Previously, Iñaki worked in data insights at Schibsted Media Group. He holds an MSc in statistical modeling.