Customer Churn Challenge

Analyse customer behaviour, predict churn risk, target retention offers, compare machine learning models, and protect fictional recurring revenue across increasingly difficult service scenarios successfully.

Challenge configuration

Generate a custom fictional dataset and choose how the round should behave.
Round0
Time--:--
Score0
Budget left$0
Revenue protected$0
Prediction progress0%

Interactive churn field

Select a customer node, inspect signals, then assign a prediction and retention response.

Customer decisions

Search, filter, rank, and edit individual predictions.
Start a round to generate customers.

Analysis workspace

Inspect model evidence, threshold trade-offs, campaign economics, and round feedback.
True positives0
False positives0
False negatives0
True negatives0
Select a customer to inspect feature contributions.
StrategyCustomers contactedCostExpected retained revenueNet value

Detected issues

IDTenureChargeActivityComplaintsContractQuality flag

Churn probability

A probability estimates how likely a customer is to leave. The threshold converts that score into a stay or churn label.

Precision and recall

Precision limits wasted offers. Recall limits missed churners. Business costs determine which metric deserves greater weight.

Class imbalance

Churners may be rare. Accuracy can look strong while the model misses most customers who actually leave.

False positives

A false positive predicts churn for a customer who stays. It can waste retention budget and reduce campaign efficiency.

False negatives

A false negative misses a real churner. This can lose recurring revenue and valuable future customer relationships.

Feature importance

Feature contributions explain why risk moved upward or downward. They support investigation but do not prove causation.

Data leakage

Leakage exposes information unavailable at prediction time. It makes evaluation unrealistically strong and harms deployment performance.

Customer lifetime value

Lifetime value estimates future economic contribution. High-risk, high-value customers can justify more expensive interventions.

Model bias

Models inherit patterns from data and design choices. Compare subgroup outcomes before relying on automated retention decisions.

Achievements

RoundScenarioModeScoreAccuracyRecallRevenue protected

Round feedback

Review missed warning signs, unnecessary interventions, and recommended next steps.
Submit a completed round to receive personalised feedback.

Export and accessibility

Save results, copy a summary, print the report, or restore locally stored progress.
Customer Churn Challenge

Related Calculators

Spam Email ClassifierFruit Classification GameWeather Type PredictorDisease Risk ClassifierLoan Approval SimulatorAnimal Species ClassifierSentiment Classification GameHandwritten Digit Challenge

Important Note: All the Calculators listed in this site are for educational purpose only and we do not guarentee the accuracy of results. Please do consult with other sources as well.