How Does Product Mix at the Store Drive Sales?

Editor’s Note: Every year, 40 or so students in the MIT Center for Transportation & Logistics' (MIT CTL) Master of Supply Chain Management (SCM) program complete one-year thesis research projects. The students are early-career business professionals from multiple countries with 2 to 10 years of experience in the industry. The research projects are sponsored by and carried out in collaboration with multinational corporations.

Joint teams of company people, MIT SCM students, and MIT CTL faculty work on real-world problems chosen by the sponsoring companies. In this series we summarize a selection of the latest SCM research. The researcher for the SCM thesis summarized below, Krishna Rajendran, analyzed the factors that retailers can take into account when deciding on the best performing product assortment policies in stores. The thesis, Parameters Driving Consumer Demand in Brazil, was completed in collaboration with a leading retail chain in Brazil, and supervised by MIT CTL's Dr. Matthias Winkenbach.

Large retail chains are increasingly faced with the question of how to develop an ideal product assortment policy to optimize sales. This issue is particularly challenging for retailers that have traditionally served customers in large cities, but are looking to serve a broader group of customers in smaller towns.

A researcher from MIT's Center for Transportation and Logistics worked with a large Brazilian retail chain and developed a mathematical model to identify the store parameters that most influence sales for different departments. This analysis could help the company formulate an ideal product assortment policy, based on the parameters of the store.

Network shift
The company has 1041 stores and 36 different departments. Up until fairly recently, its network consisted mainly of large stores of uniform sizes catering to consumers in big cities.

To cater for its established customer base, the retailer's assortment policy was to stock the same set of products at all stores. However, since 2010, it has embarked on an expansion plan to open smaller stores in small towns. Catering to more diverse consumers and opening smaller stores have necessitated a modification to the retailer's assortment policy.

The newer stores are smaller in size and will not be able to stock all products. Determining the right products to stock at these outlets is key to success. The thesis research examined 105 store related parameters. These included socio-economic characteristics of consumers (e.g. the number of salaried workers and their economic activity), presence of establishments around the store (such as schools and supermarkets), city parameters (population density, number of tourists, and university influence), and internal factors (assortment size, temperature, sales area, and inventory storage area). The aim was to identify the parameters that have a statistically significant impact on sales for each department.

Key factors
The model pinpointed a set of 10 key statistically significant store parameters that impacted five or more departments, and thus had a significant impact on the company's overall revenues. These parameters are income level of the population around the store, presence of supermarkets around the store, sales area, presence of shopping centers around the store, temperature, inventory storage area, age of the store, education level, presence of schools around the store, and the number of people in the age group 50-59 in the vicinity of each store.

The model and the insights gained from the research can be used by other large retail chains to understand the key store parameters that drive sales and to implement ideal assortment policies. These analyses can be carried out at the SKU and product line levels. Moreover, there is potential for improving the model by factoring in data on promotional campaigns.

The retail industry is very competitive, so having the right product at the right store is the key to success.

For more information on MIT CTL's Supply Chain Master's program and the student theses visit http://scm.mit.edu/program or contact SCM program Executive Director Dr. Bruce Arntzen at [email protected].

SC
MR