Start from the problem, not the dashboard.

Predict scores every player; this is the budget decision you make with it. Most retention spends the same on everyone - Sellrise ranks the base by what each player is worth and how likely they are to move, so the budget goes where it returns.

Churn and lifetime value, forecast by cohort and segment, with a plan-vs-actual alert when reality drifts from the model.

Player value tells you who is worth saving. This is the other half: deciding the timing, the offer and the channel per player - so the save actually lands.

Abnormal win and withdrawal rates, deposit-only play-through, dead affiliate sources - surfaced for review before the payout goes out.

The standard is a 14-day hold before you know if a source paid off. Acquire's goal is to call quality earlier - so you scale winners and cut dead sources while everyone else is still waiting.