Ping-Ho Ting, Steve Pan and Shuo-Shiung Chou
Cornell Hospitality Quarterly 2010 51: 492 originally published online 3 August 2010
The online version of this article can be found at: http://cqx.sagepub.com/content/51/4/492 Published by: http://www.sagepublications.com On behalf of:
The Center for Hospitality Research of Cornell University
Additional services and information for Cornell Hospitality Quarterly can be found at:
Email Alerts: http://cqx.sagepub.com/cgi/alerts
>> Version of Record - Nov 1, 2010
OnlineFirst Version of Record - Aug 3, 2010
What is This?
Downloaded from cqx.sagepub.com by guest on January 11, 2013
Finding Ideal Menu Items
Assortments: An Empirical
Application of Market Basket Analysis
Cornell Hospitality Quarterly
© The Author(s) 2010
Reprints and permission: sagepub.com/journalsPermissions.nav DOI: 10.1177/1938965510378254 http://cqx.sagepub.com By Ping-Ho Ting, Steve Pan, and Shuo-Shiung Chou
This article applies a simplified version of market basket analysis (MBA) principles to explore menu items assortments, which are defined as the sets of most frequently ordered menu item pairs of an entrée and each of five side dishes in a prix fixe restaurant. Using the PivotTable in Excel, the authors demonstrate the analysis of 3,727 transactions for meal combinations of 24 entrées and 49 side dishes, resulting in twenty-four association rules, which suggested that guests ordering a given entrée would most likely then choose a particular side dish to go with it. Applying these association rules, guests responded favorably to servers’ menu suggestions in roughly two out of three cases when the guest was “undecided” or “without preference.” This article’s chief purpose is to introduce the application of Excel that would otherwise require tedious computation if a restaurateur were to attempt it.
market basket analysis (MBA); prix fixe menu; Excel PivotTable
Market basket analysis (MBA) is one of the most commonly used data analysis techniques for marketing (Marakas 2003).
It derived its name from analyzing the orders assembled in grocery stores, when customers put purchases into their market baskets, also known as grocery carts and shopping trolleys.
The key to this analysis is the purported connections between item choices. The analysis posits that if a customer purchases one particular item, that customer is also likely to predictably purchase a second particular item. The two items may not be directly related, so by identifying the latent relationships between items purchased, shop owners can use this information to arrange store layout so that items frequently sold together can be placed in the same retail area. In the restaurant operations, MBA has been used extensively in fast-food chains for cross- and up-selling food and beverage products. Another familiar application of MBA is in online bookstores, where customers will be presented with “associated products” when they browse certain items.
Because we have seen little application of MBA in the tourism and hospitality literature (an exception is Tang, Chen, and Hu 2008), we simplified the application of MBA to identify the association (affinity) rules of two dozen dinner meals on the prix fixe menu of a Japanese-style chain restaurant in central Taiwan. The simplification involves inputting data so that it can be analyzed with Excel’s PivotTable. As often occurs in fixed-price menus, the restaurant permitted guests