> ## Documentation Index > Fetch the complete documentation index at: https://docs.orbit.devotel.io/llms.txt > Use this file to discover all available pages before exploring further. # Marketing Mix Model: split your budget across channels > Regress daily channel spend against daily revenue to see each channel's incremental contribution, ROI, a diminishing-returns response curve, and a recommended budget split — and know when to use the top-down model instead of bottom-up attribution or a holdout test. # Marketing Mix Model: split your budget across channels The Marketing Mix Model answers the budgeting question that comes *before* attribution: **given my channel spend and my revenue over time, what is each channel contributing, and how should I split the next budget?** It regresses your daily channel spend against your daily revenue, then returns each channel's incremental contribution, ROI, a diminishing-returns response curve, and a recommended budget reallocation. Because it works on aggregate daily totals, it also covers the channels bottom-up attribution cannot touch — linear TV, out-of-home, sponsorships, or any channel you only track as a daily cost total with no per-contact touch events. Run it from **Insights → Media Mix Model** in the dashboard, or over the API at `POST /cdp/analytics/marketing-mix-model`. No new instrumentation or storage is needed — it reads the same CDP event stream the attribution reports use. For full request/response schemas, see the [CDP analytics API reference](/api-reference/cdp). ## Where it fits: top-down vs bottom-up vs incrementality Three measurement surfaces answer three different questions. Pick the one that matches the question: | Question | Use | How it measures | | ---------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- | | "Of this month's conversions, how is credit split across the channels and campaigns that touched the converting contacts?" | [Multi-touch attribution](/guides/multi-touch-attribution) (bottom-up) | Joins each conversion to its per-contact touchpoints and allocates credit. | | "Did this specific campaign *cause* lift, or would those conversions have happened anyway?" | [Campaign A/B testing](/guides/campaign-ab-testing) with a holdout group (incrementality) | Compares a treated cohort against a withheld control cohort. | | "Given my channel spend and revenue over time, what's each channel's incremental contribution — and how should I split my budget?" | **Marketing Mix Model** (top-down, this guide) | Regresses aggregate daily spend against aggregate daily revenue. | Use the mix model when you are allocating budget *across* channels, when a channel has no clean per-contact join, or when signal loss makes touch-level attribution thin. Use attribution when you need per-campaign or per-model credit inside the channels you send through Orbit. Use a holdout when you need causal proof for one specific campaign — the mix model estimates, a holdout tests. ## Building a model The report needs two aligned daily series: **spend per channel** and **total revenue**. You control how each is derived: | Field | Purpose | | -------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `revenue_event` (required) | The event name whose value carries revenue, e.g. `order_completed`. | | `value_property` | JSONB property on the revenue event holding its monetary value (default `"value"`). | | `channel_property` | JSONB property on spend events holding the channel label (default `"channel"`). | | `cost_property` | JSONB property on spend events holding the spend amount (default `"cost"`). | | `channels` | Explicit channel whitelist (max 12). When omitted, the top 12 channels by total spend in the window are selected automatically. | | `since` / `until` | ISO window bounds — default the trailing 90 days, clamped to at most 180 days. | | `adstock_decay` | Carryover decay in \[0, 0.95] (default 0.3). Raise it when you believe spend keeps working for longer — brand channels; lower it for direct-response channels. | | `total_budget` | Optional per-day budget to reallocate. Defaults to the sum of each channel's own average daily spend — "reallocate what you already spend." | Minimal call: ```bash theme={null} curl -X POST "https://api.orbit.devotel.io/api/v1/cdp/analytics/marketing-mix-model" \ -H "X-API-Key: $ORBIT_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "revenue_event": "order_completed" }' ``` Practical window rules: * The fit needs **at least 14 aligned days** of spend and revenue — below that it refuses, and the dashboard shows the "Not enough history yet" state. Forty-five days + is where the fit starts to be trustworthy. * Missing days are treated as explicit zeros, not gaps — the model sees an evenly-spaced series, so a day with no spend is a real data point. * Both series must share one currency; the endpoint never converts FX. * More than 12 channels with recorded spend: the model fits the top 12 and flags `truncated_channels: true`. Pass an explicit `channels` whitelist to choose which 12. ## Reading the response The response concatenates per-channel rows with model-level fit figures. A worked example over a 60-day window with three channels: ```json theme={null} { "status": "fitted", "periods": 60, "adstock_decay": 0.3, "r2": 0.8123, "rmse": 412.37, "mae": 305.11, "baseline_revenue_per_period": 18750.42, "total_revenue": 1289340.00, "total_attributed_revenue": 164390.20, "total_current_spend": 91200.00, "total_recommended_budget": 1520.00, "truncated_channels": false, "channels": [ { "channel": "sms", "coefficient": 685.412008, "saturation_half_point": 740.00, "avg_spend": 680.00, "total_spend": 40800.00, "contribution": 118740.55, "contribution_share": 0.7223, "roi": 2.9098, "response_curve": [ { "spend_multiplier": 0, "spend": 0, "expected_revenue": 0 }, { "spend_multiplier": 0.25, "spend": 170.00, "expected_revenue": 141.03 }, { "spend_multiplier": 0.5, "spend": 340.00, "expected_revenue": 252.17 }, { "spend_multiplier": 0.75, "spend": 510.00, "expected_revenue": 342.77 }, { "spend_multiplier": 1, "spend": 680.00, "expected_revenue": 416.29 }, { "spend_multiplier": 1.25, "spend": 850.00, "expected_revenue": 475.53 }, { "spend_multiplier": 1.5, "spend": 1020.00, "expected_revenue": 523.17 }, { "spend_multiplier": 2, "spend": 1360.00, "expected_revenue": 591.26 } ], "recommended_spend": 940.00, "recommended_spend_share": 0.6184, "recommended_spend_delta": 260.00, "recommended_contribution": 496.32 }, { "channel": "email", "coefficient": 210.033991, "saturation_half_point": 380.00, "avg_spend": 420.00, "total_spend": 25200.00, "contribution": 31450.80, "contribution_share": 0.1913, "roi": 1.2472, "response_curve": [ { "spend_multiplier": 0, "spend": 0, "expected_revenue": 0 }, { "spend_multiplier": 0.25, "spend": 105.00, "expected_revenue": 50.63 }, { "spend_multiplier": 0.5, "spend": 210.00, "expected_revenue": 89.41 }, { "spend_multiplier": 0.75, "spend": 315.00, "expected_revenue": 118.46 }, { "spend_multiplier": 1, "spend": 420.00, "expected_revenue": 139.79 }, { "spend_multiplier": 1.25, "spend": 525.00, "expected_revenue": 155.12 }, { "spend_multiplier": 1.5, "spend": 630.00, "expected_revenue": 166.06 }, { "spend_multiplier": 2, "spend": 840.00, "expected_revenue": 179.19 } ], "recommended_spend": 580.00, "recommended_spend_share": 0.3816, "recommended_spend_delta": 160.00, "recommended_contribution": 157.23 }, { "channel": "direct_mail", "coefficient": 95.501122, "saturation_half_point": 420.00, "avg_spend": 420.00, "total_spend": 25200.00, "contribution": 14198.85, "contribution_share": 0.0864, "roi": 0.5634, "response_curve": [ { "spend_multiplier": 0, "spend": 0, "expected_revenue": 0 }, { "spend_multiplier": 0.25, "spend": 105.00, "expected_revenue": 21.09 }, { "spend_multiplier": 0.5, "spend": 210.00, "expected_revenue": 37.54 }, { "spend_multiplier": 0.75, "spend": 315.00, "expected_revenue": 50.36 }, { "spend_multiplier": 1, "spend": 420.00, "expected_revenue": 60.17 }, { "spend_multiplier": 1.25, "spend": 525.00, "expected_revenue": 67.57 }, { "spend_multiplier": 1.5, "spend": 630.00, "expected_revenue": 73.10 }, { "spend_multiplier": 2, "spend": 840.00, "expected_revenue": 80.39 } ], "recommended_spend": 0.00, "recommended_spend_share": 0.0000, "recommended_spend_delta": -420.00, "recommended_contribution": 0.00 } ] } ``` Read the model-level fields as fit quality and context, per-channel rows as the decision: * **`r2` / `rmse` / `mae`** — goodness of fit of the regression. Below roughly 0.5, treat every per-channel number as a hypothesis; above 0.8 the model is tracking revenue well. There is no separate confidence-interval output — `r2` and the error terms are the confidence signal. * **`baseline_revenue_per_period`** — the per-day revenue the model expects with *zero* marketing: organic demand. The intercept stays visible so "we would have made it anyway" is explicit, not folded into channel credit. * **`total_attributed_revenue` vs `total_revenue`** — the share of revenue the model allocates to channels versus everything. A small attributed share means revenue is mostly baseline — or a spend channel with real effect is missing from the model. * **`contribution` / `contribution_share`** — modelled revenue from that channel over the window, and its share of the attributed total. * **`roi`** — `contribution / total_spend`. Above, SMS returns \~2.9 per 1.0 of spend; `direct_mail` returns \~0.56 — it loses money on the fitted numbers. * **`coefficient`** — the raw regression weight in "revenue per unit of saturated spend." It can come back ≤ 0 (multicollinearity or genuinely wasted spend); such channels are clamped to zero effect for contribution and reallocation, but the raw value stays visible so you can see it. * **`saturation_half_point`** — the adstocked spend level at \~63% of the channel's maximum effect. Spending far above it buys little; it marks where the curve flattens. ## The response curve Each channel's `response_curve` samples hypothetical steady per-day spend levels at 0, 0.25, 0.5, 0.75, 1, 1.25, 1.5, and 2× its current average spend, with the modelled revenue at each. Because saturation is concave, **marginal return shrinks with every point you move right**. Read it as "expected revenue removed from the previous point": SMS above gains \~141 going from 0 to 170/day, but only \~68 from 1020 to 1360. The 1× point is where you sit today; points below it show what you give up by cutting, points above show what further spend would add. A channel with no historical spend still gets an illustrative curve off a nominal 100/day base, so its shape renders once spend starts. ## The recommended split — and its caveats `total_recommended_budget` defaults to your current average daily spend summed across channels, so the answer is "how to re-split what I already spend," not "how much to spend overall." Pass `total_budget` to model a bigger or smaller total. The allocator shifts every channel's budget to the level where the *marginal* return is equal across channels — you always fund the channel with the highest next-dollar return. Channels with a non-positive fitted effect are funded zero, exactly like `direct_mail` above. Per channel, `recommended_spend` is the suggested per-day level, `recommended_spend_delta` is the shift versus today (positive = spend more), and `recommended_contribution` is the modelled daily revenue at that level. Caveats before moving real budget: * **Correlation is not causation.** The regression associates spend movement with revenue movement; it does not prove the spend caused it. Treat the split as a hypothesis and validate the big moves with a [holdout test](/guides/campaign-ab-testing). * **Confounding lives in the window.** Promotions, seasonality, and price changes that land in the fitted window get absorbed into whichever channels moved at the same time. Refit periodically rather than trusting one vintage. * **Fit quality gates trust.** Low `r2` or a window under \~45 days means the split is a rough guide, not a mandate. * **Three channels can share the credit.** Highly correlated channels split effect between themselves — compare `coefficient` values before deciding which one the model believes. ## Prerequisites and gating * **History**: at least 14 aligned days of spend and revenue in the window; the endpoint returns 422 with `status: "insufficient_data"` below that, and the dashboard renders the history prompt. * **Data shape**: spend events must carry both the channel property and the cost property; revenue must arrive on the named event with a numeric value property. Days with no matching events count as explicit zeros. * **Role and scope**: an owner, admin, or developer key with the `contacts:read` scope — the same gate as the funnel and attribution read surfaces, since the model reads the PII-adjacent event stream. * **Rate limit**: 20 fits per minute per tenant — the fit is heavier than a plain read.