STABLE TV × MARTHA ANN (UA)
Full Funnel Impact. 180d window. Oct 28, 2025 - Apr 26, 2026.
Period window
Default: Era. Phase 1 hero, -24% / 8-week window.
Pulse · 7-14D · Apr 12 - Apr 26, 2026Tactical · 14-30D · Mar 27 - Apr 26, 2026Confidence · 30-60D · Feb 25 - Apr 26, 2026Lift · 60-90D · Jan 26 - Apr 26, 2026Phase Compare · 90-120D · Dec 27, 2025 - Apr 26, 2026Era · 120-180D · Oct 28, 2025 - Apr 26, 2026Full Arc · 180D+ · May 2025 - Apr 2026
Era read. Phase 1 hero peak. 3wk Sep 22 - Oct 12 2025. Halo CAC $12.41 vs $14.37 baseline. -14%. Peak week Sep 29 -25%. First 8 weeks averaged -24%. Halo MER 1.28×.
Operational view below. Same underlying data, alternate framings live in the methodology card. Methodology card ↓ shows all three with the math.
Era read
Phase 1 hero peak. 3wk Sep 22 - Oct 12 2025. Halo CAC $12.41 vs $14.37 baseline. -14%. Peak week Sep 29 -25%. First 8 weeks averaged -24%. Halo MER 1.28×.

Is the ad doing the work?

population default · Tellis-1988 effective-frequencyL6

The format is the ad. TV viewers watch 94% of the spot through; social viewers watch 28%. That gap is the whole reason TV moves the funnel - the ad has a chance to land. But there are two ways creative dies: showing it too often (4×/wk is the band; above that the halo decays early) and never refreshing (after 6 weeks, fatigue sets in).

Synthetic mock · methodology preview. The completion rate, VCR, frequency band, and fatigue-zone classifier below illustrate what the layer renders once a brand's creative-asset ingestion lands. CLIP / VideoMAE embeddings + Hill-curve fits populate this view at onboarding (~30d in).
Synthetic mock · methodology preview. Dashboard shell + ingestion plumbing + per-layer compute skills are scaffolded and deployed; the actual measurement engines (mix model fitter, cohort-CLV model, geo holdouts, brand-pulse LLM) wire to brand data at onboarding.
TV completion ratepremium inv.
94%
Big-screen native, sound-on, non-skippable. The ad has a chance to work.
Social video completion ratecomparison
28%
20–40% range across IG Reels, TikTok, Snap. The format is the ceiling on social.
Frequency · currentin band
3.4/wk
≤4×/wk threshold. Above 4×/wk, halo decays earlier than the model predicts.

Frequency cap simulator · halo decay onset
Industry band 4–6× per household per week · saturation onset 7–8× · "negative reach" past 8×

5×/wk
3456789
At 5×/wk frequency

Sweet spot. Halo establishes cleanly. Decay onset ~day 14, on-curve with ad-stock model.

The creative-as-lever layer. Creative is the variable that shifts every other layer's read. A great creative held at 4×/wk extends halo by 2–3 weeks vs the same creative at 6×/wk. A bad creative at any frequency just burns budget.

MethodologyHill curve + CLIP creative scoring · how this gets to v2

Frequency-fatigue model. Hill curve fit on (frequency, video completion rate/CTR) per creative: response = max · f^k / (k_half^k + f^k). Sweet-spot 4-6×/wk, saturation onset 7-8×, negative-reach past 8×. Reference: Tellis 1988 (Effective Frequency), Naples 1979. Production fit via scipy curve-fit in Python worker; this dashboard renders the fitted curve.

Creative-style scoring. CLIP / VideoMAE embeddings via HuggingFace transformers on each ad variant - runs locally in the Python worker. Cluster the embeddings to identify creative styles (humorous / aspirational / direct-response), regress style against performance per channel. Local compute, no paid VidMob dependency. ~70% of VidMob accuracy at $0/mo. Brand-of-record creative-effectiveness positioning (if needed at scale) layers VidMob on top.

Multi-armed bandit allocation. Once 2+ creatives are live + producing daily impressions, fit a bandit (Thompson sampling via mabwiser) to recommend optimal rotation weighting. Cuts creative testing time by 40-60% vs equal-rotation A/B.

Refresh recommendation. Triggered by: (a) weeks-live ≥ 4 (rotate fresh in), (b) video completion rate decayed >4pp from baseline (rotate), (c) weeks-live ≥ 6 OR video completion rate decayed >8pp (pause now). Surfaces in the dashboard as a per-creative pill.