Price Optimization Models for Retail Enterprise

How Price Optimization Models can Boost a Retail Enterprise’s Revenue

There is a difference in price optimization flow for SMB, middle, and enterprise retail businesses.

Alexander Galkin

For SMB retailers it’s necessary to compare their prices to market and apply appropriate changes. Middle stores are eager for dynamic pricing algorithms. Retail enterprises who had already covered all of the mentioned above are dealing with the need of laser-focused improvements: little changes of price are significant for their sales volumes.

Below you’ll find the best practices of price optimization for enterprise in retail.

Price Optimization Solutions

Optimization of Portfolio Pricing

The Problem

With no consideration to numerous interrelations, it’s impossible to determine precisely which products require price changes, how many of them, and when it’s better not to touch prices in order not to harm performance against the business KPIs.

By changing a price on one product, a retailer triggers a chain reaction across a group of products that are ‘neighbors’ of the repriced product in the consideration sets of shoppers. Thus, the fine-tuning of portfolio pricing architecture becomes a rocket-science task, given the thousands of latent relationships between product sales.

The Solution

In order to maximize a KPI of choice on a portfolio level, be it volume, revenue, or profit, a retailer needs optimization models that do not only have own product elasticity functions, but also include cross-elasticity coefficients with other related products. All these coefficients will be assembled in a giant equation, the solution of which will be optimal prices across your portfolio.

With such an optimization model, a retailer can implement the so-called 'differentiated' pricing recommended price changes across the portfolio in order to maximize the portfolio target of choice – volume, revenue, or profit; prediction of volume, revenue, and profit for total portfolio and for each SKU.

The varying percent of the price changes for each SKU in the portfolio, taking into account the mutual influence of competitors ('external environment' factors), and setting specific business growth goals before this action.

Data needed for this model: Item sales and price by product, competitive retailer prices for similar products — by period (day, week) for the past 3 years.

Optimization of Prices on Individual Products

The Problem

The simple division of sales, changing into price changes gives an understanding only for a ‘vacuum environment' and doesn’t support the numerous factors that also have an impact on sales.

Price elasticity is a non-linear relationship of sales volume and the price. Given its nature, it becomes quite hard to find the right price point that would produce maximized revenue (i.e., will maximize the product of the price per item and the items sold).

The Solution

By knowing the ‘elasticity function’, a retailer can find the price points that will predict with high precision how many items of a product can be sold at different price points, and maximize the parameter of choice, be it volume, revenue, or profit – at this time, for a specific product.

  • Elasticity curves for the products of choice by price points within an interval can be used for guidance and are approximations of ‘real life’, which is non-linear in nature.
  • More precise item sales, revenue and profit (optional) predictions for specific price change scenarios.
  • The list of ‘real’ competitors that have proven impact on sales, with the power of their impact indicated.

Data needed: Item sales and price by product, competitive retailer prices for similar products - by period (day, week) for the past 3 years.

Models’ Visualisation for Quick Opportunities Identification

Price Partition

The Problem

It’s complicated to know in advance what price in a customers’ perception is considered as justified. This is especially true for a product that has either the same or a different set of characteristics. Often, the pricing of certain products better suits more premium propositions, or, vice versa, shoppers wouldn’t mind paying a higher price for the product. In both cases, potential profit is lost.

The Solution

Products with similar value and set of features ‘stick together’ in a buyer's perception in clusters or segments. Shoppers are very specific about the minimum, average and maximum price they are ready to pay for products representing each specific segment.

Img legend: Scatterplot of the top 100 SKU. The X-axis is the price per piece. The Y-axis is the sales. Optional visualization—the size of the bubble is equal to sales.

Price optimization algorithms group products within a category into 'clusters,' the centers and external borders of which are visible on the chart. This graph will immediately determine which price segment a particular product belongs to, and the price variance interval which is ‘safe’ for sales.

To create a price optimization formula, and create this visualization, item sales and median price by product, by period (day, week, month) for the past year are needed.

‘Magic’ price points

The Problem

The buyer classifies the products according to her subjective 'value' indicator.

Depending on that, the shopper classifies products into price segments/categories with clear thresholds. As a result, the sales are maximized around the center of these segments and strive towards zero on their borders.

The seller’s assortment does not always take into consideration these patterns, and thus, the sales are suboptimal. Thus, during promotion planning—or in pursuit of profits—a retailer can lose sales even with a slight increase in price, or suffer in net profits because of a discount.

The Solution

There are price points in categories where sales are at their highest, as well as prices with no sales at all. Knowing these 'highs', a retailer can significantly increase sales because the probability of getting into the 'custom' price for a buyer increases significantly.

Option 1. The top X of the SKUs are taken, and they’re ranked by sales. Axis X - the price of the products. The Y-axis is sales per unit. Visual price breaks along the X-axis are thresholds of price segments.
Option 2. The sales of all SKUs in the market are taken. Products are grouped into price 'baskets', and then 'top-X SKU' approach applied.

With a price optimization system, the manager will be able to detect different price levels:

  • Those maximizing sales
  • Price 'thresholds' they better not cross.

Also, this will help you to not get into the trap of following your competitors, where they enter the 'dead zone' and lose in sales.

To draw this chart, item sales and prices (either median or weighted by sales) by product, by period (day, week, month) for the past year are needed.

'Price Ladder' or Optimal Price Intervals

The Problem

A price strategy is like a game of chess.

A retailer needs to take the best price positions by the products in order to neutralize the competition or to play on their weaknesses. This task becomes complicated, given the proliferation of categories and the high dynamics of prices.

The Solution

To outplay rivals, a retailer needs to understand the category leaders 'alignment.' At which price points are they sold most often? What the price range is: from the 'premium' price of expensive rivals to the 'convenience' price with a deep discount or a regular price in a discounter. It’s tough to keep a hand on the pulse, because prices are dynamic and change every day.

For similar products, buyers are willing to pay the same price. The price range (max — convenience price, min — promo price) also obeys this rule. The benchmark from which to build the optimal price, is the leader's most frequently encountered price. The optimal 'spread' is the leader's interval from the maximum to the minimum registered price.

Img legend: This type of chart is a 'candle/ladder chart.' The 3 points represent the minimum, maximum and median price for the observed period. On the chart, there is either the top-seller in the category, or the same product in different retailers.

A quick look at the ‘price ladder’ chart will let the retailer find quick answers to some of the toughest pricing questions – which price points am I playing now? Which ones should I play? How does my price positioning against key competitors looks like? How would I like it to look? What are the typical discounts in the category like?

Data needed to apply this price optimization technique: Minimum, maximum and median price by product by period (typically, a week or a month) by seller.

Optimal Promo Pressure

The Problem

Promotion pressure/volume on deal has increased greatly in recent years. Quite often, vendors and retailers wage ‘promo wars’ which are really tough to quit without losing sales or the market share. It’s impossible to determine which strategy to choose initially, activating and deactivating deep discounts, or offering low prices every day.

The Solution

At times, having a look at the share of volume sold on deal in total category and among the top-sellers will give you quick guidance on the promo pressure that would be optimal for the category.

Scatterplot of the top 100 SKU. The X-axis is the % of sales on deal (or the % of registered promo prices to all tracked sales cases). The Y-axis is for regular sales (or tracked sales). A scatterplot visualizing sales items and volume on deal will highlight the products that have optimal promo pressure, and those that are selling too much with a discount. And pick the moderation side.

Looking at the sales of products with different shares of promo on deal, it's easy to see who has the optimal promo percentage, and who oversells. Therefore, choose the moderate path.

Data needed: Minimum, maximum and median price by product by period (typically, a week or a month) by seller.


There are many ways retailers can improve their sales, keeping the margin healthy at the same time. Yet, any of these require implementation of retail price optimization processes, including data management, algorithmic decision making, and expert supervision. If you are an enterprise retailer and want to try the benefits of scientific price optimization, request a Competera pilot and get it on your product line.