Automatic price optimisation as a tool for small and large retailers

Author: David Klečka, CEO Yieldigo

Who deal with prices more, small or large retailers? What should the retailer that decides for price optimisation expect? Is the price optimisation matter of the team size? What are actually optimal prices and how to set them? These are the questions that we hear the most often during discussions with our retail customers.

What is the problem?

About a year and half ago, we launched a software for retailers called Yieldigo and we decided to re-open dialogue between retailers and shoppers about prices of goods. Long ago this dialogue was the initial step of any purchase and sale of goods and enabled shoppers and sellers to find the right price that was advantageous for both sides. Today if the shopper stands in front of the shelf, there is not, of course, any dialogue with the retailer. Shoppers simply got used to accept the prices. Honestly, what’s the percentage of shoppers asking for store manager to discuss price of milk?

Over the year and half we have met both small and large B2C retailers.

What have small and large retailers in common?

  • Prices are set based on competition or margin or supplier’s price recommendation. But where is the shopper as the center of interest?
  • Both sides agree that optimal price is the price the shopper understands and accepts. They believe that in the long term they will have the best economic results at this price.
  • Both sides talk about shopper’s price perception. At the same time, they can’t agree nor internally on what it actually is and how to measure it. They often mix up price perception with competition price index (which actually measures difference in prices comparing to selected competitors).
  • Both sides agree that to set the right price is extremely difficult as it’s needed to take into consideration many different factors, starting from article quality to weather forecast. They both admit that for humans it’s not possible to consider all necessary factors and that BI reports are not sufficient as they are time consuming and uninstructive to incorporate while do not guarantee any results.
  • Likewise both sides don’t know which prices are understandable for consumers and which not.
  • Both sides confuse terms price optimisation and dynamic pricing*
  • Both sides often spend money on expensive consultations and reports despite the fact that they provide only a slight advice on what to change. Additionally, this provided guideline is usually based on fixed rules and parameters which is not applicable these days as the business behind changes from day to day.

What else we noticed?

  • Small retailers look, above all, for simple but efficient application that enables to reflect different criteria, recalculate prices, both automatically, and adjust existing price settings by doing just few clicks. Thus, standard CPQ systems are not applicable as they are large and non-intuitive solutions that, moreover, do not guarantee optimal prices leading to increase in profitability.
  • Small retailers who often use the price recommendation of their suppliers see the potential in improving pricing. At the same time they are quite flexible about making price decisions.
  • Large retailers are aware of the fact that difficulty of pricing is related to the assortment scale. Therefore they are not looking for consultants who advise them but for the software that does the job instead of them.
  • Large retailers know that proper pricing is a process that needs to be done repeatedly every week, day or even hour. This applies to small growing retailers as well, especially to those in the field of e-commerce.
  • Both large and small growing retailers are thus actively looking for price optimisation tool. Small traditional retailers often do not know that there might be something that can help them with pricing and that “this something” isn’t necessarily BI tool or expensive consultation.
  • Managers of large retailers face, time to time, the pressure from middle management that refers to their many years of experience. We found out that at key assortment departments these obstinate employees can cause to their employers loss of millions of dollars per year in the net profit.
  • Small retailers have to deal with a whole range of other problems than just pricing. Once they are growing they are occupied with scalability (marketing, logistics, etc.). Once they are traditional retailers they face the problem of shortage of qualified staff.
  • The increase in profitability resulting from the change of price of only one article is, naturally, higher on the side of large retailers, where the change of price of one article has the impact on many purchase transactions.

Who is Yieldigo?
Yieldigo creates an intelligent software plugin for retailers, that is based on modern mathematical knowledge and can simulate shoppers decision making process during purchasing goods and to use this ability for setting optimal prices. The basic principles, on which Yieldigo was built, are its own scientific research in the field of mathematical stochastic methods and technological scalability that enables Yiledigo to use efficiently great computing power. Based on retailer’s data, the machine learning engine learns automatically new patterns of shoppers purchase behaviour every day which guarantees its high flexibility and ability to respond to new situations on the market.

Yieldigo serves as a plugin that is needed just to connect to the existing pricing system of the retailer and over month the retailer can see a significant increase in profitability of more than 5%. It’s like to employ a pricing manager who has the best mathematical education, has unlimited working hours, understands perfectly shoppers purchase behaviour and has many years of experience with the assortment. If a modern easy to use interface for pricing is added we get a package that is used by Yieldigo clients from retail industries like groceries, drugstores or pharmacies, brick & mortar retailers on the one hand and e-commerce chains on the other hand. Yieldigo strength is a quick integration of the plugin which takes just few weeks. 
 If you are a small retailer and you consider price optimisation we have good news for you — it’s not the matter of the team size, it doesn’t matter if you have one manager or fifty of them in your pricing team. A machine learning tool managed by one pricing manager is the right way.

 * We can meet with dynamic pricing during purchasing a flight ticket or traveling with Uber while prices change over the day according to the current short-term situations. In retail, especially in brick & mortar, similar mindset does not exist yet and prices are changed based on long-term trends over the last days and weeks and price changes are not so often. The example of dynamic pricing can be following competition prices in e-commerce which can take place even several times a day. But then we should ask — is this the optimal strategy? Isn’t there goods that can be cheaper? Or more expensive? If the answer is yes — about how much? At this point, it is the right time to start to tackle price optimisation. In other words, not every dynamic pricing method is at the same time the optimal method. The transition in this direction is non-trivial! On the other hand, the transition from optimal pricing to dynamic pricing is only a question of tool parameterisation.

Like what you read? Give Yieldigo a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.