Beat the Heat with Machine Learning to Optimize your Pricing


It is hot everywhere these days. In fact, record breaking temperatures throughout the US and Europe.  So, what impact does this have on the supply and more importantly… the price of air conditioners.

In contrast, there is the recent flooding which is creating havoc with supply chains and humanitarian assistance with food, medical supplies, and housing. Setting the right price for a good or service in times of crisis is an old problem in economic theory. With supply challenges and demand through the roof, the time for price optimization synced with supply chain planning is helping companies deal with pricing these days.

Manufacturers and distributors are taking advantage of the tremendous power of Machine Learning technology to build effective pricing solutions to address the crisis. There is a multitude of pricing strategies that depend on the company’s overall objective. While one company looks to maximize profitability on units sold, another company needs to access a new market. Different scenarios coexist in the same company for different goods or customer segments is a reality.

These are some of the crucial questions that companies face:

  • What price should we set if we want to make the sale in less than a week?
  • 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?

Given that these days it is easy for a customer to compare prices thanks to online catalogs, specialized search tools or collaborative platforms, companies must pay close attention to several variables when setting prices. Attributes such as competition, market positioning, supply chain production and distribution costs, play a key role for companies to make the right move.

Price Optimization and Demand Forecasting with Machine Learning During a Crisis

During a crisis, the market does not behave normally, historical insights typically will be of limited value in predicting future sales. Therefore, companies need to increase the importance of shorter-term information such as daily sales to predict the future.

Additionally, demand forecasting requires incorporating more near-term real-time market data than before. This means frequent updates on sales data, customer churn, sales intent, and competitors’ prices. On a broader scope, data on consumer spending, unemployment, GDP and even cities/regions may be considered for modeling future demand. Machine Learning as part of pricing optimization is being greatly leveraged to build accurate demand forecasts and optimize pricing strategies these days by accounting for nearer-term lags vs. historical data in the models.

Bottom line is that Machine Learning in pricing optimization has an enormous impact. Its strength is tied to the developed algorithms that detect and learn patterns from the data. Machine Learning models continuously integrate new information and detect emerging trends or new demands that tie back to supply planning optimization. Instead of using aggressive markdowns or promotions, companies benefit from predictive models that allow them to determine the best price for each product or service in balancing supply with demand.

What Machine Learning Does for Price Optimization

With more targeted data into the model, a price automation solution with Machine Learning will automatically price items the way they would be priced by a human expert. Machine Learning is a tremendous tool for insights:

  • In what way is the sale of air conditioners impacted when fans’ prices are drastically cut?
  • When efforts are made to sell more car batteries, are the related products, such as battery cables, recharger units, automotive tools impacted?
  • Are customers who buy certain pet foods more or less likely to buy new eating bowls the following month?
  • Are clients inactive in the last year sensitive to a promotion campaign?

Machine Learning models consider a huge number of products and optimize prices globally. The number and nature of parameters and their multiple sources and channels allow them to make decisions using fine criteria. This is an overwhelming activity if companies attempt to do it manually, or even use Excel spreadsheets.

By analyzing a large amount of past and current data, Machine Learning can anticipate trends early enough. This key value allows companies to make appropriate decisions to adjust prices. Finally, in the case of a competitive pricing strategy, Machine Learning solutions benefit from systems that continuously crawl the web and social media to gather valuable information about prices of competitors for the same or similar products, what customers say about products and competitors, and a competitor’s deals for certain products, their price history over the last number of days or weeks.

It seems natural to apply Machine Learning in the case omni-channel companies that take advantage from this technology. Though price changes are less performed in brick-and-mortar companies there is plenty of room to improve and adjust to current demand. Digital price tags now are enabling brick-and-mortar retailers to do as many price changes as e-commerce sites to match the current demand and maximize profit.

Companies using Machine Learning for Price Optimization

Price optimization has been used, with significant success, in industries such as hospitality, airline, car rental, and e-commerce retail. The hotel industry continues to employ dynamic pricing strategies, based entirely on Machine Learning. The current computational power allows prices to change practically in real time.

Airbnb proposes a dynamic price tool that recommends prices to its hosts, considering parameters such as seasonality, the day of the week or special events, and more sophisticated factors such as photos of the property to be rented or the prices applied in the neighborhood. Other companies such as eBay and Uber have adopted similar approaches. Changing prices in such a dynamic way is informally known as the Amazon effect.

Companies like Ralph Lauren and Michael Kors use Machine Learning to offer fewer markdowns and optimize their inventory in an integrated manner to increase profit margins, even at the risk of losing a little revenue. Another use case is Zara, which uses Machine Learning to minimize promotions and adapt quickly to the changing trends in demand and supply. There are many other success stories, such as Morrisons which is taking advantage of the power of Machine Learning to increase their revenues and improve operations.

Final Cooling Thoughts

Nowadays companies are changing prices more often and using state-of-the-art data driven pricing strategies to do it. Top performers across industries are nearly twice as likely to price dynamically. Whether it’s a manufacturer, distributor, or retail company, all are embracing the benefits of dynamic pricing and price optimization.

Price optimization helps understand how customers will react to different price strategies for products and services and set the best prices. Machine Learning models take key pricing variables into account to find the best prices to achieve the end goal.

The question is no longer whether to apply optimized pricing or not. But the question is how to do so to remain profitable.