> For the complete documentation index, see [llms.txt](https://docs.aloop.icustomer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aloop.icustomer.ai/ireveal/outcome-tracking.md). # Outcome tracking and holdouts Outcome tracking and holdouts in iReveal: every decision carries its result in a single trace, and incrementality is measured against counterfactuals. Analytics ends at conversions and e-commerce events; pipeline and revenue live somewhere else, and the connection between the two is asserted, not shown. iReveal closes that gap: **every decision carries its result in a single trace**, and the trace ends in pipeline and revenue impact, not pageview counts. ## The trace A trace is the full lineage from event to outcome: the visit that was captured, the identity it resolved to, the signal it produced, the decision that acted on it, and what came of that decision. Because the chain is one object, attribution is something you read, not something you model after the fact, and the record is audit-ready. The trace structure is the same one the full platform uses; see [Decisions and traces](/concepts/decisions-and-traces.md). ## Holdouts and causal measurement Correlation is what last-touch attribution sells you: what coincided with the number moving. iReveal measures **incrementality against counterfactuals**: what actually moved the number. Holdouts are how the counterfactual exists at all, a portion of eligible records held back so the lift of acting can be read against the cost of not acting. ## Alongside your MMM Marketing-mix models and geo-lift tools measure channel-level lift on aggregate data, with no pixel and no user-level tracking, and they are strongest on channels like TV, CTV, and out-of-home. iReveal is trace-level: person-, SKU-, and decision-level causality that also recovers signal and activates. {% hint style="info" %} Complementary, not substitutes: iReveal's holdouts are the calibration experiments an MMM consumes. {% endhint %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.aloop.icustomer.ai/ireveal/outcome-tracking.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.