Clear thinkers take feedback from reality, not consensus.
“Ask a consumer their preference and they will ask for the most features at the lowest price. Ask them to choose between realistic hypothetical SKUs, and their trade-off decisions reveal what they truly value.”
Great product strategy is not just about pricing. It is about understanding the trade-offs between every feature of a product, one of which is price: how features relate to one another as substitutes or complements, and how consumers trade them off at a given price and in response to price changes to find the optimal SKU-and-price combination.
Ordeen takes your team from a plain-English brief to fielded human trade-offs, a Hierarchical Bayesian model, and a shareable live market simulator in days, all inside one workspace.
We rethought every part of choice modelling, big or small.
Most research tools put the old agency process online. We took it apart instead, one step at a time, and asked of each: can this be more powerful, easier to use and faster, without giving up any mathematical rigour?
The result is a process that is more powerful, easier to run and more efficient than anything else on the market, with the rigour built in rather than bolted on.
Start with a brief. Ordeen drafts the study.
Describe the product and commercial decision you need to make, and attach any strategy deck or CSV. Ordeen extracts your features, target market, and price tiers, and recommends the right methodology out of six.
How methods are chosen →IllustrativeSeven steps from one B2B SaaS pricing study. Use the arrows to turn the cube.
One workspace. Yours within days, not quarters.
You upload the brief.
Describe the decision and attach any deck or spreadsheet. Ordeen picks the right research method, drafts the products and features to test, and checks the study design is sound before launch.
Real buyers trade off.
Launch to our integrated Prodege panel across 18 countries (~£3 to £4/complete with World Bank quotas) or your own customer list. A 60 to 90s warm-up game and automated fraud checks clean responses live.
Ordeen finds your buyer groups.
Ordeen works out what each respondent values and which features work together or compete, then groups buyers into named segments. No analyst or statistics software needed.
You test ideas and repeat.
Try different products, prices and line-ups and see the effect straight away. Share a password-protected simulator with up to 10 colleagues, download the respondent data, and repeat the study next quarter in one click.
Everything in one place. Nothing to coordinate.
A choice study usually means briefing an agency, a panel provider and an analyst, then waiting for a slide deck. Ordeen puts every step in one workspace your own team runs: one login, one invoice, and every study in one place, ready to run again.
Your study, drafted for you
Describe the decision in plain English and Ordeen sets up the study.
- Brief turned into a draft study
- Competitor products filled in
- Design checked before launch
Real buyers, without a broker
Reach the right people from inside the workspace.
- Built-in panel in 18 countries
- Or your own customer list
- Poor answers replaced for you
Results without an analyst
The modelling runs on its own once responses are in.
- Runs automatically
- Buyer groups found and named
- Quality checked on every result
One link for the whole team
Everyone works from the same live results.
- Live simulator for every study
- Private links for 10 colleagues
- Data downloads when you need them
Answers in days. Scenarios in seconds.
Speed is built into every step, not added at the end. That is what makes a live simulator possible: once responses are in, your team can test a new price or product and see the answer while the meeting is still running.
Nothing waits in a queue
Design, fieldwork, analysis and reporting happen in one place, so no step waits for another team.
The study drafts itself
Ordeen turns your brief into a study in minutes and checks the design automatically, so you can launch the same day.
Modelling in minutes
Our purpose-built engine models every respondent individually in minutes, with quality checks on every result before you see it.
Recalculated as you click
Results are prepared so the simulator updates in under a second, with a likely range on every number, even with ten colleagues using it at once.
What if we change the Pro plan?
At £39 without SSO, larger buyers choose Competitor A instead.
Try £49 with + SSO: the Pro plan gains share and revenue rises by about a half, because buyers value SSO most on the Pro plan.
Three commitments. All of them checkable.
We don't ask you to take our numbers on trust. Every diagnostic is printed on the result, every safeguard is automatic, and our entire statistical methodology is published openly.
Enforced convergence & slope refusal
An MCMC sampler always outputs numbers, even when chains never mixed. Ordeen checks split-chain R-hat, Effective Sample Size (ESS) and divergences on every fit, withholding any model that fails to converge, and refusing any WTP figure whose price slope changes sign across draws.
Posterior-expectation shares & Shapley
Plugging average utilities into a simulator washes out polarized niches, and traditional range importance changes whenever you widen the price ladder. Ordeen integrates shares across every respondent and posterior draw, and computes level-invariant Shapley importance.
Verified feature interactions & segments
Features rarely act in isolation. Ordeen models pairwise attribute interactions inside Hierarchical Bayes and applies Haldane small-cell smoothing and Benjamini-Hochberg FDR control so you only act on genuine substitute and complement effects.
Less than the cost of one consultancy study. Unlimited studies all year.
Both plans give your team the complete Choice Modelling platform, with all six methods, Hierarchical Bayes and Latent Class estimation, the live simulator, and 10 executive viewer seats on shared links. Respondents are bought at cost (~£3 to £4/complete) in non-expiring Prodege packs, or fielded to your own customer list for free.
Quarterly Plan
£10,000Per quarter · 5 creator seats + 10 live simulator viewers- All 6 methods: CBC, ACBC, Anchored MaxDiff, MBC, Van Westendorp & Gabor-Granger
- Unlimited studies and longitudinal tracking waves during the quarter
- Hierarchical Bayes & Bayesian Latent Class with convergence diagnostics
- Live Market Simulator with 95% credible intervals, WTP, 2D heatmaps & TURF
- Respondent-level CSV, XLSX, JSON & Parquet exports + segment typing tool
Standard Annual Plan
£35,000Per year · 5 creator seats + 10 live simulator viewers- Everything in the Quarterly Workspace for the full 12 months
- Saves £5,000/year compared to quarterly billing
- Continuous multi-wave tracking as competitors and market prices move
- EU-hosted in Google Cloud Belgium; DPA included; independent security reviews (April & October 2026)
- Single annual invoice for procurement; extra 5-user packs at tier rate
Price Monitoring →
Track real retail checkout prices (price + delivery), promos and variant stock across 200+ retailers in 18 countries with screenshot evidence.
Read guide →Demand Forecasting →
AI proposes external signals; econometrics validates them out-of-sample. Includes Croston/TSB intermittent demand and MinT reconciliation.
Read guide →Contract Analysis →
Analyse agreements against governing-law statute files and your company role; score portfolio risk, consolidate MSAs and draft renewals.
Read guide →Product and pricing research, with the maths in front of you.
Plain-English guides for strategy, product and pricing teams at every step from picking a method to defending the simulator in the boardroom.
Choosing the method & sample
- What is conjoint analysis?Methodology, history & use cases
- Van Westendorp, Gabor-Granger or conjoint?3 questions to pick the right tool
- CBC vs. Adaptive CBC (ACBC)When 8+ attributes need adaptation
- How many respondents do you need?Johnson's rule, 300 floor & segments
- Conditional pricing for tiers & packsAvoiding the prohibition trap
- What is Anchored MaxDiff?Best-worst scaling for 10 to 30 items
- What is Menu-Based Choice (MBC)?Baskets, add-ons & bundle pricing
- What is Van Westendorp (PSM)?4 price crossings + NMS extension
- What is Gabor-Granger?Adaptive ladders & Juster calibration
- Can LLMs replace human respondents?Why synthetic AI fails on price
The Bayesian econometrics
- Full statistical methodologyEvery equation, prior & diagnostic
- What is Hierarchical Bayes (HB)?Partial pooling & individual utilities
- Convergence diagnostics: R-hat & ESSWhy failed fits are withheld
- What is Willingness to Pay (WTP)?Buyer valuation vs. share-holding
- The Krinsky-Robb method for WTP CIsPosterior draws & slope refusal
- Tier-aware WTP: 3 ways formulas lieFixing ratio bias on tiered plans
- Shapley vs. range importanceFixing price-range distortion
- What is Nested Logit?Fixing IIA for close substitutes
- The Benjamini-Hochberg procedureFalse discovery control on pairs
- The Haldane small-cell correctionZero-cell fix in interaction tests
Simulators & industry playbooks
- Using a conjoint market simulatorPrice curves, elasticity & TURF
- Share of preference vs. market shareThe simulator caveat for decks
- What is Latent Class analysis?Mixture-model choice segments
- Latent Class vs. k-means segmentationHow to choose & why to run both
- SaaS Good-Better-Best tier pricingConditional pricing + MBC add-ons
- CPG Price-Pack Architecture (PPA)Pack sizes & Competitive TURF
- B2B roadmap feature prioritisationAnchored MaxDiff vs. Conjoint
- DTC price testing without A/B testsMapping demand cliffs safely
Bring your brief. We'll draft the market live in 20 minutes.
Walk through a live simulator with the team that built the estimation engine, and see how your product spec or pricing question maps to a study.