About us
Services
iGaming
iGaming
News
Join us
Technologies​
About us
Services
iGaming
iGaming
News
Join us
Technologies​

Case Study: iGaming Churn Intelligence from Minimal Data

Snapshot

Client: Confidential iGaming operator (name anonymized)

Period analysed: January to September 2025

Population: Approximately 500k players with at least one active day

Data used: Player ID + Activity Date (one record per player per active day)

Churn definition (empirically supported): 30 consecutive days with no activity after 31-07-2025

Churn at 30 days (with this definition): ~61% of the base

 

The business challenge

Unlike subscription businesses, iGaming has no “cancel” button: churn happens silently when players stop showing up. Acting too late wastes reactivation potential; acting too early wastes incentives on players who were just on a normal break.

This operator wanted a practical answer to a deceptively simple question:

“Who is truly at risk of churning — and who is simply taking a normal pause?”

Our approach

We deliberately started with the smallest reliable footprint possible: only Player ID and Activity Date. From that, we built a churn-risk engine in three maturity steps:

  1. Business heuristics (rules based on recency and cadence)
  2. BG/NBD probabilistic model (continuous risk ranking per player)
  3. Machine Learning (Gradient Boosting) using engineered features from the same dates

Step 0: Choosing a churn horizon that is both real and operational

We fixed 31-07-2025 as the reference date, trained on the first 7 months (01-01 to 31-07), and evaluated on August–September.

We tested churn horizons of 14, 21, 30 and 60 days, and quantified the “false alarm” risk (players labelled inactive who still return later).

Base-level return behaviour (key evidence):

  • 14 days without activity: 64% of the base, 17% returned
  • 21 days without activity: 58% of the base, 15% returned
  • 30 days without activity: 53% of the base, 13% returned
  • 60 days without activity: 38% of the base, 9% returned

 

This led to an operational conclusion for this operator: 30 days is the best balance between not triggering too early and not arriving too late.

What we built

1) Heuristics (fast baseline, easy to operationalise)

Well-designed rules based on recency and playing cadence already capture a large share of churners while flagging roughly half the base.

2) BG/NBD (probabilistic “player lifetime” model)

Using classic BG/NBD variables derived from the activity dates (frequency, recency, “age”), the model produces a continuous risk score and enables prioritisation by budget (top 10%, 20%, 30%, etc.).

3) Machine Learning (Gradient Boosting) — two flavours

We tested two ML variants with the same target: churn at 30 days after 31-07-2025.

  • Flavour A: “turbo” on top of heuristics + BG/NBD inputs
  • Flavour B: Flavour A plus additional feature engineering (e.g., active-day counts over 7/14/30/60/90, fixed windows 0–30/31–60/61–90, novelty/maturity flags including “very mature” (> 180 days observed))

Results (real numbers, same data footprint)

Global model quality (ranking churners above non-churners)

Model Type ROC AUC PR AUC
Heuristics (H1/H2) Rules
BG/NBD Probabilistic 0,90 0,89
ML – Flavour A ML (heuristics + BG/NBD) 0,93 0,94
ML – Flavour B ML (enriched features) 0,93 0,94

 

Head-to-head comparison at similar effort (~53% of the base contacted)

Approach Base contacted Precision Recall
Heuristic H1 (recency ≥ 30 days) ~53% ≈ 89,7% ≈ 78,6%
BG/NBD – top ~53% risk ~53% ≈ 89,7% ≈ 78,6%
ML – Flavour A – top ~53% ~53% ≈ 92,0% ≈ 80,6%
ML – Flavour B – top ~53% ~53% ≈ 92,0% ≈ 80,6%

Interpretation: for the same operational effort (contacting roughly half the base), ML captures more churners while reducing waste via higher precision — still using only activity dates.

What happens at different outreach sizes (ML)

Base contacted (top risk) Model Precision Recall
10% A 96,9% 16,1%
10% B 96,7% 18,6%
20% A 96,5% 31,8%
20% B 96,4% 31,8%
30% A 95,8% 47,3%
30% B 95,8% 47,3%
40% A 94,7% 62,4%
40% B 94,7% 62,4%
~49% A 93,1% 75,1%
~49% B 93,0% 75,1%
~53% A 92,0% 80,6%
~53% B 92,0% 80,6%

Why this matters (beyond metrics)

This work shows that, even before bringing stakes, margins, game types, channel, campaigns, or device data into the picture, an operator can already build a strong churn-risk engine from presence patterns alone — and then scale performance further by adding richer features later.

Request the technical note

Click the link for the full technical white paper (methods, assumptions, full reasoning, and operationalisation details). – White Paper – iGaming

Contact us

Talk to us about implementing a churn-risk engine — from quick heuristics to probabilistic models and ML, progressively and without a “big bang” redesign.

 

Carlos Santos

AI Lead

Share
Facebook
Twitter
LinkedIn
WhatsApp

Marketing and CRM

  • Marketing Automation
  •  Customer Acquisition and Retention
  • X-sell and up-sell, Propensity to Purchase
  • Segmentation
  • Advanced Campaign Criteria
  • Campaign Analysis
  • Control groups, AB testing and Uplift calculation
  • Conversion Group Analysis
  • Real time Event Processing

Maximize Your CRM and Marketing Impact with Advanced iGaming Analytics

In the competitive world of iGaming, effective Customer Relationship Management (CRM) and marketing strategies are key to driving growth and player loyalty. Our specialized analytics services empower you to optimize every aspect of your CRM and marketing efforts, from automation to real-time event processing. By leveraging data-driven insights, you can enhance customer acquisition, boost retention, and increase revenue through targeted and personalized campaigns.

 

Marketing Automation

  • Personalized Campaigns at Scale: Automate your marketing efforts with AI-driven tools that create personalized experiences for each player, ensuring that the right message reaches the right audience at the right time.
  • Multi-Channel Integration: Seamlessly integrate your marketing campaigns across multiple channels, including email, SMS, social media, and in-app notifications, to maintain consistent and impactful communication.
  • Behavioral Triggers: Set up automated responses based on player behavior, such as game activity or purchase history, to deliver timely and relevant offers that increase engagement and conversion rates.

 

Customer Acquisition and Retention

  • Acquisition Analytics: Use advanced data analysis to identify the most effective acquisition channels, optimize your marketing spend, and attract high-value players to your platform.
  • Retention Strategies: Analyze player behavior and preferences to develop targeted retention strategies that reduce churn and increase player lifetime value.
  • Loyalty Programs: Design and optimize loyalty programs based on player data, ensuring that rewards are both appealing and cost-effective.

 

X-sell and Up-sell, Propensity to Purchase

  • Cross-Sell Opportunities: Leverage analytics to identify opportunities for cross-selling complementary games or products to your players, increasing their overall spend and engagement.
  • Up-Sell Strategies: Predict which players are most likely to respond to up-sell offers, such as premium features or higher stakes games, and target them with personalized promotions.
  • Propensity Models: Utilize propensity to purchase models to predict future player actions, allowing you to craft offers that align with their likely behavior and maximize conversion rates.

 

Segmentation

  • Advanced Player Segmentation: Group players based on various criteria such as behavior, preferences, demographics, and spending patterns, enabling highly targeted marketing efforts that resonate with each segment.
  • Dynamic Segmentation: Continuously update and refine player segments using real-time data, ensuring that your marketing strategies remain relevant and effective as player behavior evolves.
  • Custom Segment Creation: Develop custom segments tailored to your specific business goals, whether you’re focusing on high-value players, new sign-ups, or dormant users.

 

Advanced Campaign Criteria

  • Multi-Dimensional Targeting: Design campaigns with advanced criteria that go beyond basic demographics, incorporating behavior, preferences, and real-time activity to create highly targeted and effective marketing initiatives.
  • Predictive Targeting: Use predictive analytics to identify the best times and channels to engage each player, maximizing the impact of your campaigns.
  • Personalization at Scale: Implement advanced criteria that allow for deep personalization, ensuring that each player receives a message that feels tailor-made for them.

 

Campaign Analysis

  • Comprehensive Performance Metrics: Track the performance of your campaigns across all channels with detailed analytics, including click-through rates, conversion rates, Uplift and ROI.
  • Optimization Insights: Benchmark campaign results and identify what works and what doesn’t, allowing you to make data-driven adjustments for future campaigns.
  • Cost-Effectiveness Analysis: Assess the cost-effectiveness of your campaigns, ensuring that your marketing spend is driving the highest possible returns.

 

Control Groups, AB Testing, and Uplift Calculation

  • AB Testing: Run controlled experiments to test different versions of your campaigns, such as varying subject lines, images, or calls to action, to determine which performs best.
  • Control Group Analysis: Use control groups to measure the true impact of your campaigns by comparing results against a baseline, providing clear insights into campaign effectiveness.
  • Uplift Calculation: Calculate the incremental impact (uplift) of your campaigns by analyzing the difference in behavior between your test groups and control groups, ensuring that you understand the true value of your marketing efforts.

 

Conversion Group Analysis

  • Understand Conversion Group: Track and analyze players that accepted your campaign and compare the conversion group to the target group to optimize your next campaign.
  • Segment-Specific Conversions: Analyze conversion rates within different player segments to understand which strategies work best for each group, allowing you to fine-tune your approach.
  • Attribution Modeling: Determine the impact of each marketing channel on conversions, helping you to allocate resources more effectively and optimize your overall strategy.

 

Real-Time Event Processing

  • Instant Response Capabilities: Use real-time analytics to respond instantly to player actions, such as placing a bet, winning a game, or making a purchase, with personalized offers or messages.
  • Live Campaign Adjustments: Adjust your campaigns on the fly based on real-time data, ensuring that your marketing efforts are always aligned with the latest player activity.
  • Event-Driven Engagement: Trigger automated campaigns based on live events, such as a player’s first deposit or a big win, to maximize engagement and retention.

 

  • Can you calculate the real Uplift or ROI from your campaigns?
  • Do you know the best channels for each type of campaign?
  • Can you Cross or Up-Sell efficiently?
  • Do you have all the variables you need to build your targets?
  • Are you capable of developing a campaign strategy?

 

If you got at least one No to these questions or if you want to go to the next level, talk to us!

Analytics & Data Science

We put Analytics to your service. The Insights you need, at the right moment, in the right place, to the right person.

Data is everywhere. Data is growing faster than ever, either structured or unstructured, so the ability of extracting insights from Data is the challenge that moves us.
We deliver the Insights you need.

What is Analytics?

Analytics by definition is the systematic computational analysis of data or statistics, or simply the science of logical analysis. But today we use a broader definition and we can say that Analytics involves analysing historical data from different sources to find trends, effects of past decisions or events, or measure performance, and then apply this knowledge to improve Business.

Analytics Maturity Model

For each step you go up in the Analytics Maturity Ladder, the bigger will be the Value you add to your business. The complexity also rises in each step, and it’s very difficult to jump steps, here is where Pluto Analytics’ wide experience deploying and improving Analytical Systems can help you.

  • Do you have all the information you need when making decisions?
  • Do you spend more time analysing information rather than collecting it?
  • Do you have the same business numbers of all the other members of your company?
  • Do you feel that you are one step ahead of your competitors?
  • Do you think that your company is efficient dealing with business information?

 

If you got at least one No to these questions or if you want to go to the next level, talk to us!