COD

    Catch disengagement at onset — not after silence

    Who has already decided to leave? COD reads the early bend in a player's engagement and flags the onset, while the player is still reachable and the save is still possible.

    15–30%

    churn reduction via earlier intervention

    Flagged at onset

    not after the silence

    Regulated-ready · Pseudonymised inputs · DPA available

    Ranges are modelled estimates; actual results vary by operator data and maturity.

    The Challenge

    By the time the report says "churned," the player is already gone

    The industry counts days of inactivity: seven for regulars, fourteen for casual players, thirty before a player is filed as lost. By day one of silence, the decision to leave is already weeks old. The behavioural shifts that precede disengagement are visible long before the silence; standard reporting just isn't built to read them. COD reads the week before the silence, while intervention can still change the outcome.

    How It Works

    How COD surfaces the onset of disengagement

    Behavioural signals flow in. COD flags the players whose engagement is beginning to slip — and routes them to your retention team while the window is open.

    The decline starts while the dashboard still says active. COD reads the bend, not the silence.

    Forecasting

    How many active players will you have in 30 days?

    Retention signals answer one question at a time: this player, this week. Your month still gets planned on last month's actuals. The CRM calendar, the bonus budget, the VIP coverage, all committed before anyone knows what the base will look like when the money lands.

    COD's player-level signals roll up into active-player forecasts at brand, market, or product level. The same model that flags who is drifting tells you how many will still be there in 30 days, so the month is planned on where the base is going, not where it was.

    Plan CRM and bonus budgets on the coming month, not the last one
    Set VIP coverage before the peak arrives, not during it
    Track forecast against actuals until the number earns your trust

    See the play: How many active players will you have in 30 days?

    Output

    What your retention team actually receives

    Not a churn score in a dashboard. A flag on the players slipping now — in time to do something about it.

    At-risk player flag

    Each player whose engagement is bending downward is flagged at onset, on the player record your team already works.

    Onset timing, not lagging status

    The signal fires when the decline begins — not weeks later when the player has already gone quiet.

    Built for your retention workflow

    Delivered into the CRM, retention automation, or alerting your team already uses — no new tool to check.

    Value

    How teams use churn onset detection

    Intervene while it still works
    Reach players at the first sign of slipping, while a well-timed touch can still change the trajectory.
    Stop wasting win-back spend
    Win-back campaigns fire after the player's already gone. COD moves the spend earlier, where it actually converts.
    Protect revenue before it leaks
    Catch the decline in active, valuable players before the churn shows up in next month's numbers.
    Delivery

    How COD is delivered

    Live in weeks, not quarters — here's the path

    You send: player-day activity exports.
    You get back: decision-grade flags in the tools you already use — Retention · Alerting · BI.
    Runs in our cloud or on-prem in your own environment — pseudonymised inputs, no direct identifiers, every decision auditable.
    See full integration details →
    Two ways to start

    Pilot — for existing operators

    Test whether COD's onset signals are accurate and useful against your own player base.

    Explore the Pilot →

    Cold-Start — for new operators

    Calibrate churn-onset detection from regulated-market priors before you have your own engagement history.

    Explore Cold-Start →

    The exact scope is tailored to each operator's stage, data, and goals.

    Catch onset while the window is open

    Book a 20-minute discovery call — we'll show you what churn-onset detection looks like against your data.

    Book a Discovery Call

    Explore the other engines

    D1LTV — Day-1 lifetime valueEVIP — Early VIP identification

    Related reading

    Cookies and Privacy

    HumanGraph may use cookies or similar technologies to support core website functionality and understand site usage. Essential cookies are always active and cannot be disabled.

    Optional cookies (analytics and marketing) will only be activated with your explicit consent. You can change or withdraw your consent at any time.

    Learn more in our Privacy and Cookies pages.

    Essential

    Required for the website to function.

    By clicking "Save Preferences" or "Accept All", you consent to the use of optional cookies as described in our Privacy and Cookies pages.