THE SCIENCE OF CLEARANCE SALES (May 7, 1998)

The authors have created a mathematical model that can be applied by computer at each of a chain's individual stores. It sets an optimal price and adjusts inventories during end of season clearance, the last phase of a product's life after regular and promotional sales. The researchers designed their model to draw on data from point of sale (POS) databases that retailers use to retain and track product sales.

The model is incorporated into a retailer's decision support system for ease of use. It determines a table of recommended clearance markdowns as a function of store inventory level and projected sales for the remainder of the season for which the model is applied.

Moneymaker in Marginal Business
Clearance markdowns often total several hundred million dollars per year for major retail chains. Given the thin margins of many retailers, the effectiveness of clearance markdown policies can make the difference between a profitable and unprofitable season.

Setting clearance pricing and inventory policies, though, is a challenge when individual stores in a large chain have different levels of demand for individual products. There is an advantage to setting clearance prices at the store level to account for variations in inventory levels and sales rates across stores. But existing systems often apply the same markdown regionally or nationwide due to the complexity and time-consuming nature of the decision.

The model takes this special need into account. It also takes into account special features, including seasonal variations in sales rates.

The analysis applies when the rate of sale is sensitive to inventory level — when sales rates drop as inventory falls below a certain level. In general, the authors conclude, the initial clearance markdowns should be deeper than buyers are accustomed to taking, while excessive markdowns at the end of the season should be avoided in favor of donating products to charities, or even discarding, unsold merchandise.

Test Cases
At the time the paper was written, the researchers had tested the model at three retail chains and reported two successes.

In the most recently conducted test case, a chain with 300 stores, the model was tested for one complete season in the infants and toddlers area. Comparing clearance results with the previous year and projecting to the entire chain, the savings would represent a $45 million increase in revenue and gross profit dollars.

In a second case, a chain with over 600 stores, the system increased profitability by $10 million annually, despite the fact that buyers at the chain were initially reluctant to follow the researchers' steep markdown recommendations and instead took a more conservative approach.

In the third case, a chain with 800 stores, the model didn't produce superior results during initial testing. A subsequent analysis showed that the researchers were hampered by inexact inventory and sales figures, as well as some incorrect assumptions about the retailer's sales. The retailer is currently completing a revised system that more closely integrates the company's merchandise planning process, the appropriate databases, and the recommendations by the clearance markdown model.

The study, "Clearance Pricing and Inventory Policies for Retail Chains," was written by two management scientists, Dr. Stephen A. Smith and Dr. Dale D. Achabal of the Leavey School of Business, Santa Clara University, Santa Clara, California. It appears in the current issue of Management Science, a publication of INFORMS.

The Institute for Operations Research and the Management Sciences (INFORMS) is an international scientific society with 12,000 members, including Nobel Prize laureates, dedicated to applying scientific methods to help improve decision-making, management, and operations. Members of INFORMS work primarily in business, government, and academia. They are represented in fields as diverse as airlines, health care, law enforcement, the military, the stock market, and telecommunications.