Choosing the Right Price
Choosing the right price for a product or service is a challenge as old as the concept of economics itself. There are a huge number of pricing strategies that you can choose from to support your company’s brand and objectives. One company may seek to optimise on the overall market share, while another company may seek to maximise profitability on every unit it sells for the next month. Indeed, nearly every company we work with has numerous and differing price strategies across their product categories and customer segments.
In this article, we’ll take you through the opportunities and challenges in price optimisation for retail and how retailers should be taking advantage of the tremendous power of Machine Learning (ML) technology to build effective pricing automation solutions.
With industry leaders like Walmart, Amazon, and Target setting the standard, having your prices managed in real-time is becoming an increasingly important feature for most retailers. These big-name brands shrewdly utilise powerful proprietary algorithms to make their offers nearly impossible to beat. While Amazon blazed the path forwards, Walmart has aggressively sped up its digitisation in the last five years to catch up. In the face of this, there are some of the crucial questions that retailers currently face:
What is the fair price of this product, given the current state of the market, the period of the year, the competition, or the fact that it is a rare product?
What is the price we should set if we want to optimise both the likelihood of sale of the product and the overall margins of this product across time.
These days, it is very easy for a customer to compare prices thanks to online catalogs and price comparison websites. Thus retailers must pay close attention to several parameters when setting prices.
It is because of the need to continuously consider this significant number of variable data sources that ML is the approach utilised by leading retailers. Machine Learning’s ability to consider numerous variables simultaneously coupled with its ability to optimise toward a variety of objectives is why it is the best-in-class approach for price management. ML models can continuously integrate new information and (additional data streams if they become available/pertinent) and detect emerging trends or new demands. The more advanced decision making ML approaches are even trained in simulation so that they know the optimal strategy when they encounter new market conditions.
The use of ML is a very attractive approach for retailers. Instead of using, for example, aggressive general markdowns (which is often a bad strategy), they can benefit from predictive models and even decision making models that allow them to determine the best price for each product or service.
What is price optimisation?
Price optimisation uses predictive analytics and decision making machine learning to pursue one key objective: Find the best price for a product. It achieves this by understanding the competitive landscape, seasonality, general demand and company priorities.
Pricing Optimisation systems have evolved since the relatively simple strategies of the early 1970s, such as a standard markup to base cost. Now, Price Optimisation systems are capable of accurately predicting the demand of products or services, and deciding upon the best price to optimise toward, given the business’s specific objectives.
Current state-of-the-art techniques in price optimisation allow retailers to consider factors such as:
The Difference Between Price Optimisation and Dynamic Pricing
It is important to differentiate price optimisation from dynamic pricing given that these terms are sometimes used as synonyms.
The first point is that Dynamic Pricing is a single pricing strategy, while price optimisation can be set to optimise toward any given price strategy.
Dynamic Pricing is the strategy of adjusting prices by significant amounts in a temporal manner in response to swings in demand. It is especially powerful in circumstances where total market supply is fairly restricted - such as airplane seats and taxis on the road.
In contrast, price optimisation techniques consider many more factors to suggest a price or a price range for different scenarios (e.g. initial price, best price, discount price, etc.).
Dynamic pricing for retail is something that should be used with extreme caution. Customers are very accustomed to price changes in retail where the price change is often to reduce the price or to match a competitor. However if a retailer puts their price up significantly when they identify a shortage of supply throughout the market and across their competitors (like Uber does), this can be poorly received. Customers might feel that prices are unfair or that the company is practicing price gouging. Dynamic pricing is, to belabour the point, a strategy to be used with extreme caution.
How to apply Machine Learning for Price Optimisation.
The pricing strategies used in the retail world have some peculiarities. For example, retailers can simply determine the prices of their products by accepting the price suggested by the manufacturer (commonly known as MSRP). This is particularly true in the case of mainstream products.
While these and other strategies are widely used, ML enables retailers to develop more complex strategies that work far better to achieve their sales goals and KPIs. ML techniques can be used it in many ways to optimise prices. Let’s have a look at a typical scenario.
Say you’re a brick and mortar retailer with a significant online presence. You are aware that your customers (even many of those who buy in-store) are checking prices online before they purchase. Therefore, you adopt a very popular and powerful strategy (its popularity is due to its effectiveness), competitive pricing.
This strategy defines the price of a product or service based on the prices of the competition.
What data you need for our Price Optimisation ML
Before you can take advantage of the power of Price Optimisation ML, you need to feed data into the platform. To train Machine Learning models, it is necessary to have different kinds of information:
Transactional Sales Data: The Sales History of each product.
Competitor data: prices applied to identical or similar products.
Inventory data - specifically, stock levels across stores & DCs
Product Descriptions: a catalog with relevant information about each product such as category, size, brand, style, colour, photos and manufacturing or purchase cost.
Why Price Optimisation with Machine Learning?
There are a number of reasons the leading retailers are using Machine Learning in their Price Optimisation.
Firstly, ML models can consider a huge number of products and optimise prices globally. The number and nature of parameters and their multiple sources and channels allow them to make decisions using fine criteria. This is a daunting task for retailers to undertake manually, or even using basic software.
Secondly, ML can be integrated with online web crawlers and social media streams to monitor critical information about competitor prices and promotions.
Companies using Machine Learning for price optimisation
Here at Remi AI, we specialise in Machine Learning for Price Optimisation and Supply Chain Optimisation. Since 2013, we have worked with a wide range of companies such as Coca Cola, Microsoft, PwC, Winc, and other major (as well as several smaller) retailers, to leverage the power of decision-making ML to optimise their operations.
Working with these companies we’ve seen the impact of what is common sense: pricing is a critical factor in a company’s profitability, market positioning, and general success.
Each of the companies we have worked with have different pricing priorities, but the impact of price optimisation has been fairly universal. Retailers especially face narrow margins and competitive pressures. Price optimisation has become a critical tool in helping retailers set the best prices to remain competitive.
If you’d like to learn more about Machine Learning and Price Optimisation, checkout our website here.
If you're ready to start maximising your pricing opportunities, try 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 mailing list for great news from us and the other knowledgeable folk in the market.