CMOtech Canada - Technology news for CMOs & marketing decision-makers
Canada
Analytic Partners adds experimentation to GPS Enterprise

Analytic Partners adds experimentation to GPS Enterprise

Fri, 20th Nov 2026 (Today)
Mara Sugue
MARA SUGUE News Editor

Analytic Partners has integrated its Agile Learning experimentation tool into its GPS Enterprise platform, aiming to give marketers a single system for running tests and using the results in broader decision-making.

The update brings the experimentation product, previously offered on a standalone basis, into the wider analytics platform. The integrated setup is designed to let businesses run tests when they do not yet have enough time or data for a full model, then feed those results into marketing mix modelling and scenario planning.

At the centre of the change is what Analytic Partners calls decontamination, a process designed to remove outside influences that can distort the outcome of marketing experiments. These can include promotions, stock shortages, weather, competitor activity and other media activity during a test period.

According to the company, its ROI Genome data shows that more than two-thirds of marketing experiments are contaminated. It says this can produce misleading findings and lead marketers to direct budgets towards the wrong channels or activities.

One example cited involved a go-dark test for a large retailer. In that case, Analytic Partners said decontamination identified USD $40 million in potential lost revenue that had not been visible in the raw result.

The GPS Enterprise platform combines business data with the company's own benchmark and performance information. It is used to compare scenarios, forecast outcomes and test strategies before larger spending decisions are made.

Its ROI Genome intelligence layer draws on more than 25 years of global performance benchmarks, according to Analytic Partners. The company says this information underpins both the experimentation and modelling functions inside the platform.

Paul Sinkinson, Managing Director of Australia and Asia at Analytic Partners, said flawed testing is becoming a wider problem as marketers rely more heavily on experimentation in a tougher budgeting environment.

"Experiments have become marketing's favourite answer to a tough year, but most can't see what's distorting their results. A promotion, a stock-out or a competitor's push can all change the outcome. Every test gives you an answer, but only a decontaminated one tells you what to do," Sinkinson said.

Sinkinson said the issue does not stop with a single inaccurate result. Contaminated findings can carry through into other forms of analysis if they are used as inputs for broader models, he said.

"Test results are increasingly being fed into marketing mix models. A contaminated test doesn't just give one wrong answer, it steals credit from other channels and hides the real reason sales moved. That's why our experiments and our models run on the same data, in one platform," he said.

Platform updates

Alongside the integration of Agile Learning, Analytic Partners has added several other functions to GPS Enterprise. These include Pulse Updates, which provide interim insight between full model refreshes; Live Forecasts, which adjust as market conditions and investment plans change; and Dynamic Intelligence, which incorporates macroeconomic forecasts into planning.

Agile Learning can design geographic, store and audience tests, match test and control groups across multiple business attributes, and remove contamination before passing the results into modelling and forecasting tools, according to the company. Where no comparable market is available, it can create a synthetic control for the test.

Analytic Partners' broader argument is that experimentation should not sit apart from commercial analysis. Instead, tests, models and forecasting should work from the same underlying evidence so organisations can make decisions across marketing, pricing, brand and finance with fewer gaps between teams and systems.

Sinkinson said experiments are particularly useful when organisations are dealing with new products, channels or pricing approaches that have limited historical data. In those cases, he said, testing can create an evidence base before a wider rollout.

"Experimentation is crucial where historical data doesn't exist yet. It lets organisations test strategies in-market and build evidence before rolling them out more broadly," he said.

He said the company sees measurement as one part of a wider commercial decision-making process rather than an end in itself.

"An experiment is only worth running if it changes what you do next. Most businesses can't wait months for a model to tell them whether a new channel, price or product will work, so they test. The real value comes when that clean, decontaminated result feeds straight into the model and into scenario planning, so every test makes the next decision faster and better informed," Sinkinson said.