Artificial Intelligence for Dynamic Pricing

Dynamic pricing, a practice started by American Airlines in the 1980s,  is now becoming an important tool for e-commerce retailers and other  businesses. Widespread in both the air travel and hotel industry, and  famously well executed at Amazon, companies are now utilising dynamic  pricing to respond to changes in demand and to drive significant  increases in revenue. Remi AI’s Dynamic Pricing platform for example  typically delivers a 17% average increase in monthly revenue across the  SKUs when introduced (This figure obviously varies across industries  and products).


American Airlines pioneered Dynamic Pricing the 1980s


In the age of e-commerce, where customers can now easily compare prices  between multiple suppliers in a matter of seconds, price is now  considered the greatest factor in the purchasing decision. A recent US  survey found that 80% of survey participants considered price the single  most important factor in a purchase.

“80% of survey participants considered price the single most important factor in a purchase.”

In  the last 10 years, Artificial Intelligence and Machine Learning Models  have had a large impact on Dynamic Pricing methods. With greater  customer segmentation and the ability to analyse hundreds of thousands  of SKUs, these methods have become the best performing approaches to the  challenges of pricing and dynamic changes in pricing strategies.

Although they are complex models, these Dynamic Pricing machine learning models are grounded in a very simple concept:

Deliver the right price for every customer while increasing revenue for the business.

Even  a small retail business with only a few core products will have a wide  range of customers with different tastes, values and budgets. For one of  our recent clients we ran user bucketing and uncovered over 40  different customer types. Each of these different customer types  displayed different preferences and buying behaviours.

With  any artificial intelligence that is controlling dynamic prices, its  primary responsibility is to uncover the fundamentals of the supply  demand curve for each SKU in your product range and then price  effectively against that curve to increase revenue. Supply and demand is  perhaps one of the fundamental concepts of economics and it is the  backbone of a market economy.

Demand  refers to how much a product or service is desired by buyers. The  quantity demanded is the amount of a product people are willing to buy  at a certain price; the relationship between price and quantity demanded  is known as the demand relationship.

The relationship between price and quantity

As many  of you will know, traditionally the higher the price of the good, the  lower the quantity demanded.The lower the price, the greater the demand  for the good.

For  the inverse, Supply represents how much the market can offer. Quantity  supplied refers to the amount of a certain good producers are willing to  supply at a given price. The correlation between price and how much of a  good or service is supplied to the market is known as the supply  relationship. Price, therefore, is a reflection of supply and demand.

As  technologies for Machine Learning (ML) and Artificial Intelligence (AI)  become more advanced and the dimensions of available data expand,  dynamic pricing is going beyond its traditional inventory management  function and enabling companies to understand this demand relationship.  Pricing is becoming intelligent and continually adjusting to changing  consumer behaviour and demand preferences, while also responding to  organisational inventory and marketing requirements as well as other  external pricing influences.

Today,  Artificial Intelligence approaches such as Remi AI’s dynamic pricing  platform is enabling enterprises to marry rich data sets with  sophisticated pricing models and apply our artificial intelligence  techniques. The product is pricing alternatives across thousands of  product stock keeping units (SKUs). These offers are also uniquely  tailored to the individual consumer dynamically at the point of  engagement, and thus more likely to generate a sale.

The Remi AI approach to dynamic pricing.

Across our clients, the algorithmic approach changes, but there are  three fundamental steps in our dynamic pricing pipeline that are  important to understand.

Stage 1. Customer Clusters

In the context of customer segmentation, cluster analysis is the use of a  mathematical models to discover groups of similar customers based on  finding the smallest variations among customers within each group. These  homogeneous groups are known as “personas”.

Customer segments

Arguably the greatest advancement that machine learning has brought to  dynamic pricing has been the highly accurate customer segmentation.  Older approaches treated the customer base a homogeneous whole, whereas  the reality is that every company has a wide range of customer personas.

Stage 2. Understanding Demand Relationship for every ‘persona’.

Here our AI platform models the demand relationship for every ‘persona’.  A simple example of this is as follows; users who are searching for two  cases of beer for delivery at 9:00pm on a Friday are happier to pay a  higher price for the product.

Stage 3. Vary the price depending on the customer, time of day and other key factors.

With  a strong understanding of the demand relationship and the different  buying personas of our customers, we start to bring our Reinforcement  Learning AI to bear on the sales channels, changing the prices of each  individual SKU at regular time intervals.

What is the AI actually trying to achieve?

This  depends on your company’s objectives. Some of our customers have their  dynamic pricing focused on increased conversions, in which case the  platform is weighted toward lowering prices and others are focused  heavily on increasing total revenue. If the AI is weighted toward  increasing total revenue, it often will increase margins on numerous  SKUs by a reasonable percentage.

The benefits that these methods bring are:

  • Intelligent control on Pricing Strategy
  • Enabler for Growth in Revenue
  • More precise, SKU level prices
  • Faster response to demand fluctuations
  • Price  changes take into account more factors including customer price  perception, leading to long terms increases in sales or profits

For  those looking to bring Artificial Intelligence into their business  operation, Dynamic Pricing can yield significant increases in revenue.  For more information, please visit our site

Alasdair Hamilton — CEO

Remi AI

Stay tuned on the Remi AI blog as we build out the complete supply chain offering!

Or, if you're ready to start seeing the benefits of A.I-powered inventory management, start the journey here.
Who are we?

Remi AI is an Artificial Intelligence Research Firm with offices in Sydney and San Francisco. We have delivered inventory and supply chain projects across FMCG, automotive, industrial and corporate supply and more.
Want to know more? Sign up to our newsletter for the latest information from us and other knowledgeable folk in the market.
Thankyou
We'll be in touch soon.
Oops! Something went wrong while submitting the form.
Recent Posts
See All

Find opportunities in your data