Leading companies in the transportation, hotel and retail sectors use analytical techniques such as data mining and revenue management to improve profits. But the powerful combination of the two used together has been little explored. In novel research, ITOM professors Amit Basu and John Semple and MBA student Surya Rebbapragada of SMU Cox show how the combination of these analytic methods can be used by universities to improve the overall quality of the students they enroll.

While the study highlights how the combination would work in the college admissions process, the approach can be applied in hiring or other business situations involving time sensitive offers. "As the economy becomes more service-based, being able to price and maximally exploit a market is becoming very valuable using revenue management techniques. With today's analytics, companies are able to extract more meaning and insights from company data, which they have in vast quantities."


The Study

The innovation in this study is the combining of two powerful techniques. "College admissions have not gone through much innovation," Basu says. "We wanted to see how we could change this by proposing new techniques to provide a new perspective on the problem of identifying and getting the best possible students." MBA student Surya Rebbapragada, with an engineering background, had taken both data mining and revenue management courses at Cox and wanted to independently study the combination of the two techniques. A collaboration was born.

The competition for college admissions is getting fiercer each year with a record number of applications for most colleges. The acceptance rate in some elite colleges is as low as 10%, so talented students often apply to schools in the next tier; students apply to multiple schools, with each school having its own timelines and deadlines for admissions. Thus, students are often caught in a dilemma when they run out of time to accept an offer from a university that is lower on their priority list, before they know the decision from a university they value more. The college admissions process is thus extremely stressful and unpredictable to students and parents.

Universities, on the other hand, usually receive far more applications than their capacity.
Performance indicators and their associated weights, used by universities to make decisions, are often based on a best guess approach relying mostly on past experience. However, since not all admission offers are accepted, universities send out offer letters and scholarship offers and hope that the best students accept, and then have to find alternates later from a weaker pool if they have too many unfilled seats

Data mining and revenue management techniques can be used to turn a lose-lose into a win-win situation. By applying these techniques, universities can methodically score an applicant and be able to respond almost immediately with an offer. In the approach proposed by the researchers, data mining predicts the quality of the applicant using historical student performances and other key factors from the student's application. Revenue management techniques are used to generate a "going rate" for the student, that is, the quality of the applicant to the university. This helps guide the decision of offering admission at different points in the admissions process. The student then knows the university's decision soon after they apply, and the university benefits from maximizing the overall quality of the student it admits.

Companies such as airlines and hotels use revenue management techniques to maximize their revenue by collecting the best price possible for each seat/resource. Thus, a university's efforts to maximize the overall quality of the students it admits--filling each seat with the best possible student-- is comparable to revenue management in the service industry.  Similar to the service industry maximizing the price for each seat, the authors use revenue management techniques help select the best applicant when the quality and quantity of future applicants is uncertain.

However, instead of a price, the value or the quality of the applicant is compared against a "going-rate" derived by revenue management techniques, to make a decision. The bid price or a "going-rate" table can then be used as a reference by the admissions office to accept or deny a particular application. By using these bid prices as a reference, the university can maximize the overall quality of admitted students, and at the same time make a decision on the application quickly.


Combining data mining and revenue management

With the spread of information technology most industries collect large amounts of data, often organized into data warehouses. A number of data mining techniques have been developed over the last few decades that provide the intelligence to find patterns in historical data. These patterns can be used to enhance the customer experience and improve revenues and profitability.

In recent years, the growing importance of "perishable" products in the service economy has motivated the development of special methods for pricing such products. Revenue management thus deals with demand-management decisions for perishable products or products whose value changes over a finite lifetime during which demand can vary. The basic idea behind these techniques relies on identifying different classes of customers and then exploits the differences in their willingness to pay. Revenue management has been very successful in developing dynamic pricing strategies for services such as lodging, travel and healthcare. It can aid decision making in situations where there is uncertainty in demand. 

According to Basu, "While both techniques are popular in different domains, using them together is still quite novel."  He notes that companies like Sabre Systems may use sophisticated analytics including both revenue management and data mining, but this is not widely reported in the news media. Basu explains, "Smart companies recognize that they can utilize these two techniques for competitive advantage. They are a natural fit, with the strengths of the two methods complementing each other."


"Use of Data Mining and Revenue Management Methodologies in College Admissions"
by Surya Rebbapragada, Amit Basu and John Semple is forthcoming in Communications of the ACM, 2009.


Summary by Jennifer Warren.