Pricing by Objectives: How AI Learns to Set the Right Price
Goal-based pricing starts with the target outcome (margin, revenue, category competitiveness) and lets AI calculate the prices needed to achieve it, rather than piling on rules one product at a time.
The engine simulates thousands of scenarios by factoring in business constraints, purchasing behavior, and product cannibalization; if the objective is unattainable, it identifies the best compromise.
For retailers supported by Booper: a margin increase of 1 to 3 points in just a few months and a 70% to 90% reduction in pricing preparation time. The pricing manager retains the final decision.
For years, setting prices meant piling up rules product by product, then looking back to see if the margin had held up. This method has reached its limits: inflation, consumers who can compare prices in a matter of seconds, and more aggressive competition. Artificial intelligence now makes it possible to start with the desired outcome —an increase in revenue, a margin point, or making a product category more competitive—and work backward to determine the prices needed to achieve it. Here’s what this shift means in practice for retailers, based on twelve years of pricing projects conducted at Booper.
Why Pricing Has Become a Strategic Issue for Retailers
For a long time, pricing was treated as a technical, almost confidential matter, the importance of which varied depending on the sensitivity of the current senior management. This is paradoxical, because it encompasses three major responsibilities: profit margin, in-store traffic, and, ultimately, the company’s overall performance.
Three developments have been game-changers since the COVID-19 pandemic. Successive bouts of inflation and cost volatility are forcing retailers to manage their product mix and profitability with much greater precision. Price transparency has increased with e-commerce and online marketplaces: a customer can compare two offers in a matter of seconds, and a retailer’s price reputation is built (or destroyed) much faster than before. Finally, advances in data structuring and AI are making possible what was once impossible: simulating scenarios, anticipating purchasing behavior, and ensuring the reliability of decisions before implementing them.
Pricing has thus evolved from an operational function to a strategic management tool—a shift that we detail in our guide on fair-pricing methods and margin management. In fact, this is one of the blind spots we encounter most frequently: many companies still do not have a dedicated pricing function.
A lot of data, but few truly effective pricing decisions
Contrary to a still-widespread belief, access to data is no longer the problem. Retailers have access to rich and reliable information: sales receipts, sales histories, inventory levels, purchase prices, competitor price data, and even external data such as weather forecasts.
What’s missing is the ability to turn this information into decisions. Many companies have the tools and the data, but lack a structured, shared, and sustainable pricing strategy. The result is predictable: prices set category by category, without a big-picture view, and trade-offs that change depending on the situation at hand.
AI offers a serious solution to this shortfall because it enables a shift from reactive pricing to predictive pricing (we discussed this during the webinar “Is Your Pricing Predictive or Still Reactive?”). However, this requires models that are precise and fast enough to handle tens of thousands of SKUs. That’s where the difference lies: anticipating sales, simulating scenarios, and streamlining decision-making. To understand how these models estimate customer reactions to a price change, see our article on price elasticity and AI.
Pricing Governance That Breaks Down Silos
Historically, pricing decisions were made by a single function (sales, procurement, or product development) using siloed approaches, and there were often separate files for pricing, procurement, and category management. This model is no longer viable for one simple reason: price affects margins, volumes, brand positioning, and the customer experience all at once. None of these areas can be managed in isolation.
The approach that works for our clients is more collaborative. The pricing team sets the framework and broad guidelines; category managers and buyers contribute their on-the-ground knowledge to refine decisions. This collaboration is based on structured validation processes, clear approval workflows, and tools that track every decision. The goal is twofold: to ensure sound decision-making and to align the various business units toward a shared understanding of performance. We’ve detailed this organizational structure in an article dedicated to collective governance of pricing decisions.
From Fixed Pricing Rules to Goal-Based Pricing: What AI Is Really Changing
Goal-based pricing is a pricing method that starts with the desired business outcome (margin, revenue, competitiveness) and uses AI to calculate the prices needed to achieve it, rather than applying rules set on a product-by-product basis.
This is probably the most profound change. In the past, a retailer would set pricing rules on a product-by-product basis and then assess the impact on its bottom line after the fact. Today, we can approach the problem from the other direction: by starting with the objective. Generate several million euros in additional revenue, improve the margin by one percentage point, and strengthen competitiveness across three key product categories.
Based on this objective, the engine simulates thousands of scenarios while taking into account both:
- business constraints (minimum margin, psychological price thresholds, consistency across formats and brands);
- observed purchasing behaviors, by product line and by store;
- strategic guidelines specific to each brand (loss leaders, positioning relative to a particular competitor, price image to be maintained).
If the target is achievable, the system suggests the price paths that lead to it. If it is not, it identifies the best possible compromise and explains why. This second scenario is often the most useful: it prevents the executive committee from being promised a result that the market will not allow. For the simulation mechanics themselves, see “From Price Calculation to Impact Simulation” and our method for testing a price before launching it.
profit margins generated in just a few months by retailers supported by Booper, based on the results observed in our projects (figures presented by Booper in *Informations Entreprise* magazine, September 2026).
| Dimension | Rule-Based Pricing | Pricing by Objectives |
|---|---|---|
| Starting Point | One rule per product or product family. | A specific business target to be met. |
| View | The rearview mirror: you measure after the fact. | Forecasting: We run simulations before making a decision. |
| Scope | Each price is optimized individually. | The performance of a department, a store, or the network. |
| If the goal is out of reach | We find this out at the end of the period. | The best compromise is identified early on. |
Anticipate cannibalization rather than optimizing a single metric
The value of a pricing model lies not only in the quality of its sales forecast, but also in its ability to anticipate the indirect effects of a decision. A price cut can boost sales of one product while negatively impacting two similar products in the same aisle: sales volume for that product increases, but the category’s margin declines.
That is why our models incorporate intra-category cannibalization, as measured bycross-elasticity and the halo effect. We optimize the performance of a category or a store as a whole, not a single metric in isolation. In practice, this is often what distinguishes a tool that “boosts sales” from one that actually improves profitability.
Generative AI and Price Execution: What's Changing for Pricing Teams
Until now, pricing teams have spent a significant portion of their time creating simulations and then analyzing the results manually. This phase will be largely automated. We are working on a new generation of tools capable of analyzing the performance of a store, a category, or an entire network in real time, and then automatically generating operational recommendations that are explainable and auditable.
the time required to prepare prices observed among Booper's clients once the simulation and analysis processes had been standardized (figures presented by Booper in *Informations Entreprise* magazine, September 2026).
The goal is not to replace human expertise. It’s about shifting the focus of the role toward analysis, oversight, and decision-making. AI identifies strengths, flags areas for attention, detects anomalies, and suggests corrective actions—all with a level of detail that no team could maintain manually. The pricing manager retains control over the final decision: this is the logic we describe in “AI Decides, AI Executes.”
We call this stage“price execution”—in other words, the ability to move from analysis to action much more quickly and on a large scale. It also opens up international opportunities, particularly in markets where promotional pressure is high and price management becomes very complex. For the logical next step in this trend—with AI agents continuously adjusting prices within defined safeguards—see our analysis ofAgentic Pricing.
How this plays out in practice
Booper was founded in 2014 with a simple belief: pricing deserves the same level of analytical rigor as supply chain management or marketing. Twelve years later, the team consists of about 30 retail and pricing specialists, including four PhDs in AI and data science. Since its founding, about 50 companies have entrusted their pricing to Booper, including 30 major clients currently active in France and abroad (notably Vietnam and Thailand). For a concrete example, see the case study of a food retailer that switched to predictive pricing.
in managed sales and more than 4,000 retail locations whose prices are managed using Booper tools, in France and internationally.
An engine that starts with your goals, not your rules
The BOOPER MPS solution combines explicit business rules with AI models: you set the objective (margin, revenue, competitiveness by category), the engine simulates scenarios, factors in cannibalization, and presents you with possible pricing trajectories, along with their rationale. No decision is implemented without validation through your approval processes.
What purpose do you want your prices to serve?
Schedule a meetingIf you want to apply these principles as part of a comprehensive process—from diagnosis to in-store implementation—our guide to retail pricing optimization covers every step.
Frequently Asked Questions
Short answers to the most frequently asked questions about goal-based pricing.
What is goal-based pricing?
Goal-based pricing involves starting with the expected business outcome (revenue growth, margin points, competitiveness within a category) rather than relying on rules set on a product-by-product basis. An AI engine then simulates thousands of pricing scenarios, taking into account business constraints, purchasing behavior, and the retailer’s strategy, and proposes the paths that will achieve the objective—or the best compromise if the objective is out of reach.
Why do retailers struggle to turn their data into pricing decisions?
Data is rarely the problem: sales receipts, sales figures, inventory levels, purchase prices, and competitor data are all available. What’s most often missing is a structured pricing strategy that’s shared across departments, as well as models that are fast and accurate enough to analyze this data across tens of thousands of SKUs.
How does AI account for cannibalization between products?
The models estimate how a price change for one product affects sales of similar items. Instead of optimizing each price individually, the engine optimizes the performance of an entire category or store, which prevents gaining volume on one product at the expense of the department’s margin.
What is "price execution"?
This is pricing execution: the ability to move quickly and systematically from analysis to action. AI tools analyze the performance of a store, a category, or a network in real time, detect anomalies, and generate operational recommendations that the pricing team validates.
Will AI replace pricing teams?
No. It automates the creation of simulations and the manual analysis of results, which used to take up a large portion of the teams’ time. The focus of the job is shifting toward analysis, oversight, and decision-making: the pricing manager sets the objectives, evaluates the proposed scenarios, and retains the final approval authority.
Sources
Interview with Hugues Lafitte, “When AI Learns to Set the Right Price,” *Informations Entreprise*, IT & Digitalization section, September 15, 2026. Key figures and client results: Booper data published in the same interview. Last updated: September 29, 2026.
Goal-based pricing starts with the target outcome (margin, revenue, category competitiveness) and lets AI calculate the prices needed to achieve it, rather than piling on rules one product at a time.
The engine simulates thousands of scenarios by factoring in business constraints, purchasing behavior, and product cannibalization; if the objective is unattainable, it identifies the best compromise.
For retailers supported by Booper: a margin increase of 1 to 3 points in just a few months and a 70% to 90% reduction in pricing preparation time. The pricing manager retains the final decision.
The key takeaway: An AI-generated price recommendation without an explanation falls on deaf ears with pricing teams, who refuse to apply a score they don't understand.
Explainability and auditability are two distinct requirements: the former justifies a recommendation at the time it is proposed, while the latter makes it possible to trace who approved what, when, and why—even several months later. A key finding: Explainability is identified as a key AI risk by a large majority of executives, but very few organizations are actually taking steps to address it.
Fixed-rule dynamic pricing is giving way to autonomous AI agents that make decisions in real time—on both the seller and buyer sides—without waiting for a human approval cycle.
90% of B2B purchases will be handled by purchasing agents by 2028 (Gartner), and 47% of the retail sector has already adopted agent-based AI (NVIDIA): competition between agents is becoming the norm, not the exception.
The real risk is not speed but the lack of safeguards: price floors, price ceilings, and explicit governance are becoming the priority, lest algorithmic collusion—which regulators are already scrutinizing—occur.