Owner role · Evaluation planner
Evidence: The days 1–5 versus 6–8 split is recorded before rule selection.
Forecast evaluation / Delivery leads, planning owners and acceptance reviewers
Readiness checklistFreeze a forecast evaluation cutoff before fitting
Separate held-out task outcomes from evidence used to choose the forecast rule.
The artifact checks outcome leakage into fitting, separate from retaining a forecast vintage or rolling origins.
Opens the current invite-request page. Access is subject to approval; this example is not imported automatically.
Original worked case · Manual planning resource
Inspect the decision, not just the summary.
Start with the invented evidence, follow the reasoning, and retain its limits when adapting the brief.
01 · Inspect the inputs
Every record stays visible
| Evidence window | Declared use | Proposed actual use |
|---|---|---|
| Days 1–5 | Fit rule | Fit rule |
| Day 6 | Held-out outcome | Evaluate |
| Day 7 | Held-out outcome | Used to choose parameter |
| Day 8 | Held-out outcome | Evaluate |
Use horizontal scrolling for wide tables. These records are invented, not customer data.
02 · Follow the reasoning
How the case leads to a decision
The three declared held-out days include day seven. Using that outcome to select the rule violates the stated information boundary even if the final reported score uses all three rows.
The bounded result
The proposed rule has seen part of its held-out outcomes, so the declared evaluation is contaminated. Preserve the cutoff and choose a genuinely unseen evaluation or an explicitly different scope.
Definitions and method context
Records, decisions and policies are original synthetic examples. External references supply context; they do not validate these cases or TeamBoostAI capabilities.
Forecasting: Principles and Practice — accuracy ↗
Genuine held-out forecast and point-error evaluation context. Binary scoring examples use their own explicit toy definitions; no real task model is validated.
External references checked 6 October 2026. Demand for these topics has not been measured.
Check the evidence before proceeding
Local readiness checklistSynthetic planning case: A manual evaluation declares days 1–5 for fitting and days 6–8 held out. A proposed parameter choice uses day-seven outcomes before claiming performance on days 6–8.
Owner role · Reviewer
Evidence: Day-seven outcome influenced parameter choice rather than being unseen evaluation evidence.
Owner role · Method owner
Evidence: A new untouched cohort or transparently revised claim is chosen; contamination is not erased from history.
0 of 3 checks marked locally.
Checking boxes records your review here; it does not verify product data or save anything.
Decision to make: The proposed rule has seen part of its held-out outcomes, so the declared evaluation is contaminated. Preserve the cutoff and choose a genuinely unseen evaluation or an explicitly different scope.
Filled manual planning note
Invented planning text. Adapt it to your evidence and confirmed owners.
The proposed rule has seen part of its held-out outcomes, so the declared evaluation is contaminated. Preserve the cutoff and choose a genuinely unseen evaluation or an explicitly different scope. The three declared held-out days include day seven. Using that outcome to select the rule violates the stated information boundary even if the final reported score uses all three rows. The cutoff alone does not validate sample size, features, timing or forecasting performance.
Put the outline to work
- Freeze fitting and test identities. Check: The days 1–5 versus 6–8 split is recorded before rule selection.
- Inspect every information use. Check: Day-seven outcome influenced parameter choice rather than being unseen evaluation evidence.
- Restore a valid declared evaluation. Check: A new untouched cohort or transparently revised claim is chosen; contamination is not erased from history.
Questions about this workflow
Can held-out data be examined eventually?
Yes for evaluation; using it for tuning changes what that same cohort can support.
Does this require a specific train/test percentage?
No. This example checks information boundaries, not a universal split ratio.
Does this create tasks in the product?
No. The brief is a manual planning resource. Use the product access link to check onboarding and the workflows available in your account.
From a useful outline to team work
Explore TeamBoostAI for your team
Use the owned checks and downloaded brief to discuss this planning decision alongside your TeamBoostAI tasks. Confirm available fields, roles and account features separately. The example is manual; it does not calculate live analytics, create work or run an experiment in the product. Confirm the workflows available in your account before adopting this outline.
Request TeamBoostAI access
Opens the current invite-request page. Access is subject to approval; this example is not imported automatically.