Ekimetrics review

Adequate — 3 of 5 on this rubric’s scale, from Poor (1) to Excellent (5). This dimension carries 25% of the total score.

Benchmark — across the 16 other agencies evaluated in this discipline, this dimension runs Excellent 1 · Strong 4 · Adequate 11. The typical agency here scores Adequate, and 5 of them score higher than this one.

What this dimension measures: The heaviest weight, because an unvalidated model is an opinion with decimal places. Look for a described methodology, stated assumptions, and above all how the model is VALIDATED: holdout periods, backtesting, or reconciliation against a real experiment. A described method with no validation story scores 3.

Scores high — A firm that publishes its validation approach and names its limits scores 4-5.

Scores low — 'Proprietary algorithm' with no methodology at all scores 1-2 — proprietary is not a method, and in this category it is the single least checkable claim a vendor can make.

What we found — Method is described openly across a public education library: /measurement-explained sets out MMM (econometric modelling on aggregate weekly/monthly data), attribution, incrementality testing and triangulation, and lists eight named measurement challenges including data quality, attribution's partial channel picture and time-to-insight lag. The FAQ article states a concrete input requirement -- 3 to 5 years of history, 'between 36 to 160 monthly observations, or 150 to 250 weekly observations' -- and concedes 'small sample sizes can lead to reduced model accuracy', with Bayesian methods discussed for short series. What is missing is a validation story for their own delivery: across six methodology pages read, there is no holdout period, no backtest or out-of-sample procedure, no fit or accuracy metric, and no described model-diagnostic pack. The only validation mechanism named is the general principle that 'incrementality experiments are best used to validate and calibrate MMM outputs'. Names its limits well; does not publish how the model is checked, so it sits at the rubric's 'described method, no validation story' band. That is between the two bands, which is why it scored Adequate.

On the record — “Published methodology page explains MMM, attribution, incrementality testing and triangulation, enumerates required data inputs, and names eight measurement challenges including data quality, attribution's partial channel view and time-to-insight lag.” ekimetrics.com ↗

On the record — “Published data requirement: 3 to 5 years of historical data, stated as 36 to 160 monthly or 150 to 250 weekly observations, with an admission that small samples reduce model accuracy.” ekimetrics.com ↗

attribution — working out which marketing touch actually caused a sale. Good practice names its model and its blind spots; bad practice quotes each ad platform’s self-graded numbers, which overlap and overclaim.

Evidence: vendor stated — the agency’s own claim, recorded as theirs rather than ours.

Adequate — 3 of 5 on this rubric’s scale, from Poor (1) to Excellent (5). This dimension carries 20% of the total score.

Benchmark — across the 16 other agencies evaluated in this discipline, this dimension runs Excellent 1 · Strong 7 · Adequate 4 · Weak 4. The typical agency here scores Strong, and 8 of them score higher than this one.

What this dimension measures: Whether the firm can establish causality rather than only correlation: geo holdout tests, matched-market design, PSA/ghost-ad tests, switchback designs, or reconciliation of modelled results against live experiments.

Scores high — Named experiment designs with described execution score 4-5.

Scores low — Correlation-only modelling with no experimental capability scores 2-3 — legitimate and common, but the buyer should know they are buying a correlational estimate. A firm that presents modelled attribution as proven causality scores 1-2, and the overclaim should be named in the verdict.

What we found — Two experiment designs are named and correctly described in the incrementality article: user-level randomized controlled experiments, and geo testing where 'matched geographic regions serve as treatment and control markets' to measure causal impact of TV, OOH or retail activation. The article names real preconditions -- sufficient traffic for statistical significance, 'a clean holdout that doesn't contaminate the control group', enough elapsed time for delayed purchase -- and concedes that for low-spend channels the cost of a rigorous test can exceed its value. It also states experiments calibrate MMM where historical data is sparse. No PSA/ghost-ad or switchback design is mentioned. Crucially, nothing read says Ekimetrics designs or runs these tests for clients: the content is educational, and none of the five case studies read describes an executed experiment or a modelled-vs-measured reconciliation. So the capability is claimed in principle and unevidenced in practice. No overclaim was found in the other direction -- attribution is described as showing contribution to conversions, never as proven causality. That is between the two bands, which is why it scored Adequate.

On the record — “Two experiment designs are named -- user-level randomised controlled experiments and matched-market geo testing -- with stated preconditions (statistical power, an uncontaminated holdout, time for delayed purchase) and the statement that experiments validate and calibrate MMM outputs. The page does not state that Ekimetrics executes these tests for clients.” ekimetrics.com ↗

On the record — “Five named client case studies are published with described engagements: Accor, Haleon, Eurostar, Pierre & Vacances-Center Parcs, and Jaeger-LeCoultre/IWC.” ekimetrics.com ↗

attribution — working out which marketing touch actually caused a sale. Good practice names its model and its blind spots; bad practice quotes each ad platform’s self-graded numbers, which overlap and overclaim.

Evidence: vendor stated — the agency’s own claim, recorded as theirs rather than ours.

Strong — 4 of 5 on this rubric’s scale, from Poor (1) to Excellent (5). This dimension carries 15% of the total score.

Benchmark — across the 16 other agencies evaluated in this discipline, this dimension runs Excellent 1 · Strong 8 · Adequate 6 · Weak 1. The typical agency here scores Strong, and 1 of them score higher than this one.

What this dimension measures: Attributable client work at a stated scale and category. Treat any 'we found X% waste' claim as a vendor-stated number unless a client is named and corroborates it.

Scores high — Named clients with described engagements score 4-5.

Scores low — Anonymised case studies score 2-3 — common here for genuine confidentiality reasons, so do not penalise beyond the band, but do not credit unverifiable lift figures either.

What we found — Five named case studies read or listed first-hand on /success-stories: Accor (group-wide MMM across France, Germany, UK, Australia, Brazil, full-funnel econometric models, 100+ internal users of the output), Haleon (five-year global always-on measurement build, ~80% of brands and markets, 1,000+ marketers trained), Eurostar, Pierre & Vacances-Center Parcs, and Jaeger-LeCoultre/IWC. The Haleon study carries an attributed quote from a named client-side executive, John O'Connor, Marketing Analytics Director at Haleon -- an unusually checkable form of reference for this category. A further logo wall names Nestle, Estee Lauder, Renault, Tim Hortons, Specsavers, BlaBlaCar, Groupe SEB and Auchan without accompanying studies. Not Excellent because every performance number is vendor-published and none is corroborated by the client: '12% media contribution to sales', 'six consecutive quarters of media contribution growth' and 'incremental revenue through optimized budget reallocation' are Ekimetrics' own figures, and the Accor result is described qualitatively with no lift number at all. That is the high band above, which is why it scored Strong.

On the record — “Five named client case studies are published with described engagements: Accor, Haleon, Eurostar, Pierre & Vacances-Center Parcs, and Jaeger-LeCoultre/IWC.” ekimetrics.com ↗

On the record — “The Haleon study carries an attributed quote from a named client-side executive (John O'Connor, Marketing Analytics Director, Haleon) and reports MMM refresh cycles moving from 24+ weeks to roughly 8 weeks, enabling quarterly optimisation.” ekimetrics.com ↗

funnel — the path from stranger to customer — awareness at the top, purchase at the bottom. “Full-funnel” means owning the whole path, not one stage.

Evidence: partly checkable — corroborated in part against the sources below; the remainder rests on the agency’s own account.

Strong — 4 of 5 on this rubric’s scale, from Poor (1) to Excellent (5). This dimension carries 15% of the total score.

Benchmark — across the 16 other agencies evaluated in this discipline, this dimension runs Strong 10 · Adequate 4 · Weak 2. The typical agency here scores Strong, and none scores higher than this one.

What this dimension measures: What the engagement needs from the buyer (spend, conversion, and channel data at what granularity) and — critically — whether the firm also buys the media it is measuring. A firm that measures media it does not sell is structurally more credible; where the same firm buys and grades its own work, that conflict must be disclosed and should be named in the verdict whether or not the firm names it.

Scores high — Clear data requirements plus independence from media buying scores 4-5.

Scores low — Undisclosed conflict scores 1-2.

What we found — Independence from media buying appears structurally intact: nothing across the homepage, seven solution and about pages, or five case studies offers media planning, buying or resale, and the Accor study describes governance involving local and regional marketing teams, corporate finance, and 'the media agency' as a separate third party -- i.e. Ekimetrics grades spend it did not place. Data requirements are published at a useful level: the measurement ecosystem diagram on /measurement-explained enumerates the inputs (TV/radio/OOH, paid search, paid social, CRM, brand tracking, sales performance, macroeconomic factors, competitor activity, first-party interaction data) and the FAQ states the required history depth in observations. Short of Excellent because per-channel granularity, the minimum viable data spec, and what happens when a client's data fails the observation-count threshold are nowhere stated, and independence is established by absence of a contrary offering rather than by an explicit disclosure statement from the firm. That is the high band above, which is why it scored Strong.

On the record — “The Accor engagement describes governance involving local and regional marketing teams, corporate finance and marketing leadership, and 'the media agency' as a separate party -- consistent with Ekimetrics measuring media it does not buy.” ekimetrics.com ↗

On the record — “Five named client case studies are published with described engagements: Accor, Haleon, Eurostar, Pierre & Vacances-Center Parcs, and Jaeger-LeCoultre/IWC.” ekimetrics.com ↗

CRM — customer relationship management system: the database of record for contacts and deals — HubSpot, Salesforce and kin.

Evidence: partly checkable — corroborated in part against the sources below; the remainder rests on the agency’s own account.

Adequate — 3 of 5 on this rubric’s scale, from Poor (1) to Excellent (5). This dimension carries 10% of the total score.

Benchmark — across the 16 other agencies evaluated in this discipline, this dimension runs Excellent 1 · Strong 6 · Adequate 9. The typical agency here scores Adequate, and 7 of them score higher than this one.

What this dimension measures: What arrives and how often: a one-off model, a refreshed quarterly model, a live dashboard, a decision workshop. A model delivered once and never refreshed is a snapshot of a market that has moved, and should be scored as the ceiling it is.

Scores high — Stated deliverables with a stated refresh cadence score 4-5.

Scores low — Undefined deliverables score 2.

What we found — Cadence is stated once, inside one client's outcome rather than as a published standard: the Haleon study reports refresh cycles moving from '24+ weeks to ~8-week MMM model refreshes, enabling quarterly optimisation'. That is a genuine always-on cadence and rules out the one-off-snapshot ceiling. The Accor study likewise describes a persistent platform centralising data, scenarios and budget recommendations for 100+ users. Against that, the solution pages and /eki-decisions describe the deliverable abstractly -- 'one shared performance model', 'embedded governance before execution', 'a decision system' -- and never state what a buyer actually receives: which artefacts, which dashboards, how many models, what workshops, over what engagement length. Whether Eki.Decisions is licensed separately from the consulting, and on what terms, is not stated anywhere read. That is between the two bands, which is why it scored Adequate.

On the record — “The Haleon study carries an attributed quote from a named client-side executive (John O'Connor, Marketing Analytics Director, Haleon) and reports MMM refresh cycles moving from 24+ weeks to roughly 8 weeks, enabling quarterly optimisation.” ekimetrics.com ↗

On the record — “Five named client case studies are published with described engagements: Accor, Haleon, Eurostar, Pierre & Vacances-Center Parcs, and Jaeger-LeCoultre/IWC.” ekimetrics.com ↗

deliverability — deliverability: whether cold email actually lands in the inbox rather than spam. The tell is infrastructure talk — warmed sending domains kept separate from your main domain — because a burned domain outlasts the engagement.

Evidence: vendor stated — the agency’s own claim, recorded as theirs rather than ours.

Weak — 2 of 5 on this rubric’s scale, from Poor (1) to Excellent (5). This dimension carries 10% of the total score.

Benchmark — across the 16 other agencies evaluated in this discipline, this dimension runs Strong 2 · Adequate 3 · Weak 11. The typical agency here scores Weak, and 5 of them score higher than this one.

What this dimension measures: Note any minimum spend and whether the model licence continues after the engagement ends.

Scores high — Published fees, ranges, or a stated engagement structure with numbers score 4-5.

Scores low — A described structure without numbers scores 2-3. Bespoke-only with no anchor scores 1-2.

What we found — No fee, range, minimum, day rate, or engagement structure with numbers appears anywhere across the homepage, /solutions/marketing-effectiveness, /eki-decisions, the case studies or the FAQ article. Every page terminates in a contact form. There is no stated minimum media spend below which the engagement is not viable, and no statement of whether the model or the Eki.Decisions licence continues, and at what cost, after the engagement ends -- a material question when the deliverable is an always-on refreshed model rather than a one-off study. Bespoke-only with no published anchor. That is what the low band describes, which is why it scored Weak.

On the record — “No pricing, fee range, minimum engagement size or day rate is published on any page read; every path ends at a contact form.” ekimetrics.com ↗

deliverability — deliverability: whether cold email actually lands in the inbox rather than spam. The tell is infrastructure talk — warmed sending domains kept separate from your main domain — because a burned domain outlasts the engagement.

Evidence: inferred — our reading of indirect evidence, not a documented fact.

Stronger here: Nepa scores Strong on the same dimension.

Adequate — 3 of 5 on this rubric’s scale, from Poor (1) to Excellent (5). This dimension carries 5% of the total score.

Benchmark — across the 16 other agencies evaluated in this discipline, this dimension runs Adequate 5 · Weak 11. The typical agency here scores Weak, and none scores higher than this one.

What this dimension measures: Independent, verified reviews or checkable references. Low weight deliberately: measurement work sells through procurement and referral, so a thin public review footprint is normal and the method evidence above matters far more.

Scores low — A substantial verified base scores 4-5; a handful scores 2-3; none located scores 2.

What we found — No client review base could be read first-hand: the Clutch profile URL returns 404 and the G2 product reviews page returns 403 to fetching, so no rating or review count is cited here in either direction. What does exist is third-party analyst evaluation. The Forrester Wave: Marketing Measurement and Optimization Services, Q1 2026 is real and independently confirmed -- Forrester's own listing shows a report covering '12 Providers That Matter Most', and Ipsos MMA, Gain Theory (WPP) and Analytic Partners each published their own Leader announcements from the same report. Ekimetrics' Leader placement in it, and the Visionary placement in the 2025 Gartner Magic Quadrant for Marketing Mix Modeling, were read only on Ekimetrics' own pages; the Forrester report itself is paywalled at $2,995 and its criteria scores could not be read. Analyst placement is a checkable reference of a kind, but it is not client review evidence, which is why this does not reach the top band.

On the record — “The Forrester Wave: Marketing Measurement and Optimization Services, Q1 2026 is a real report covering 12 providers, but its vendor placements are paywalled ($2,995) and Ekimetrics' Leader placement could only be read on Ekimetrics' own page.” forrester.com ↗

Evidence: partly checkable — corroborated in part against the sources below; the remainder rests on the agency’s own account.