Skip to content
iGaming Times

Choose your emails

Which emails would you like?

Independent industry intelligence in your inbox. We will email you a link to confirm the emails you ticked, and every email carries a one-click unsubscribe link. Each list can be left on its own.

TECHNOLOGY & PRODUCTPlayer Data Science:Value, Harm, Fraud andExperimentationAdvanced · 6 lessonsiGaming Times Learning

Player Data Science: Value, Harm, Fraud and Experimentation

Advanced
1h 48m
6 lessons

The models an online gambling operator runs on its customers, and how to build them so they can be defended. The course covers the data an operator holds and the feature layer built on it, lifetime value and churn models and the uplift experiments that make interventions pay, responsible gambling risk models from markers of harm through the label problem to the decision layer regulators inspect, fraud and integrity models against an adversary (bonus abuse, multi-accounting, payment fraud, laundering, suspicious betting) and the rules, supervised, anomaly and graph methods that stack against them, experimentation under extreme variance and regulatory constraint, and model governance: inventory, documentation, validation, explainability, fairness, automated-decision rights and monitoring.

Written for data scientists, analysts and engineers working in or joining a gambling operator, and for the compliance and product people who own the decisions those models drive. It assumes working knowledge of statistics and machine learning.

The through-line: these models make regulated decisions about real people, so the harm model constrains the commercial models and not the reverse, and every decision must be explainable to the person it affects.

What you will learn

  • Describe the event streams and customer record an operator holds and the blind spots in them
  • Choose between cohort curves, buy-till-you-die models and supervised prediction for a given LTV decision
  • Map markers of harm to features in the event data and explain why relative features beat absolute ones
  • Distinguish bonus abuse, multi-accounting, payment fraud, laundering, collusion, suspicious betting and advantage play
  • Design an experiment with the right unit, population, metric, duration and sample size
  • Maintain a model inventory with risk tiers that scale the controls

Who it is for: data scientists, analysts and engineers working in or joining a gambling operator, and for the compliance and product people who own the decisions those models drive. It assumes working knowledge of statistics and machine learning.

Before you start: A working knowledge of gambling products and industry terminology will help. Read our iGaming basics course if you need a foundation.

Lessons are free to read without signing in. Sign in to save progress. Completion records your progress through this course; it does not confer a professional licence or regulator approval.

Related explainers

Need a quick reference alongside the lessons? Start with these guides.

Lessons

  1. 01

    The Data and the Questions

    16 min

  2. 02

    Value and Retention Models

    18 min

  3. 03

    Responsible Gambling Risk Models

    20 min

  4. 04

    Fraud and Integrity Models

    18 min

  5. 05

    Experimentation Under Variance and Constraint

    18 min

  6. 06

    Governance and Explainability

    18 min

Cookie Preferences

Choose which cookies you want to accept. Essential cookies are required for the website to function properly.

Required

Necessary for the website to function. Cannot be disabled.

Help us understand how visitors interact with our website.

Used to deliver relevant advertisements and track ad performance.

Remember your preferences and settings for a better experience.