Developing a price optimization strategy used to be a complicated affair that involved various marketing research, in-store and online testing, analytics and consumer surveys — and even focus groups.
But advances in technology are simplifying the process. And in a test involving Rue La La Inc., Groupon and B2W Digital, MIT professor of engineering systems David Simchi-Levi deployed a three-step approach that leverages data analytics and machine learning to boost the top and bottom lines.
In a research report on the test, the professor, from MIT’s Institute for Data, Systems and Society, said there’s a “new frontier” of price optimization as “businesses start to take advantage of advances in machine learning, increases in computing speed, and greater availability of data.”
Simchi-Levi told WWD that he “developed a way to set optimal prices for hundreds of stock units — in near real-time, and on an ongoing basis.”
“In trials of our pricing technology with three online retailers [Rue La La Inc., Groupon and B2W Digital], we found that we were able to increase each retailer’s revenue, market share and profit for selected products by double-digits,” Simchi-Levi said in his report. “What’s more, although the examples described in this article involve online retailers, the price optimization method we developed is also appropriate for brick-and-mortar retailers; we recently implemented a similar method at a brewing company, where we optimized the company’s promotion and pricing in various retail channels with similar results.”
The MIT scientist said with Rue La La, one challenge was to price goods that were new to the market. “The company refers to them as ‘first-exposure’ items, and they account for the majority of its sales,” Simchi-Levi noted in the report. “For example, in one department, about half of the first-exposure items sold out before the end of the event — suggesting that Rue La La could have raised prices on those items while still achieving high sell-through.”
Simchi-Levi went on to say that on the other hand, “many first-exposure items sell less than half of their inventory by the end of the sale period, indicating that their prices may have been too high.”
The MIT team deployed Simchi-Levi’s three-step process over a period of time and the results were surprising. “We quantified the financial and market impacts of our tool for styles in various price ranges using a field experiment with Rue La La that lasted six months and that included 6,000 products,” he said in the report. “In the end, the decision support software led to a 10 percent increase in revenue for the company. This increase in revenue translated into a direct impact on profit and margin.”
The three-step process starts with forecasting, where Simchi-Levi and his team matched “a cluster of products with similar sales characteristics to those of the product being optimized.” Using a “regression tree” machine learning process, the MIT scientists created a prediction. “Using a company’s historical sales data, our algorithm generates as many as 20 ‘if-then’ statements that can be used to predict the relationship between demand and price. That information, in turn, can be used to generate a price.”
The next step was to learn by testing prices against actual sales and reconfiguring the pricing curve to match the actual results. “At the end of the learning period, we know how well the product sold and can use that information to refine our demand-price curve for it,” he added.
The final step is to optimize. “Once the learning period is over, we apply the new curve and optimize pricing across hundreds of products and time periods,” Simchi-Levi said.