Prof. Georgia Perakis

John C Head III Dean, Interim
William F Pounds Professor of Management
Associate Dean of Social and Ethical Responsibilities of Computing
Professor of Operations Management and Operations Research and Statistics
Co-Director, Operations Research Center (ORC)

Assistant

Tammy Holmstrom
tholmstr@mit.edu

Areas of Interest and Expertise

Airlines
Auctions
Competition
Electronic Commerce (E-Commerce)
Inventory
Mathematical Programming
Operations Management and Research
Optimization
Pricing
Revenue Management
Transportation
Management Science (MS)

Recent Work

  • Video

    Georgia Perakis - 2019 Management Conference

    March 13, 2019Conference Video Duration: 36:28

    Spotting Influential Retail Customers for Targeted Offers with Machine Learning

    Online shopping has given rise to a wealth of data previously unavailable to retailers. This data has created new opportunities for companies to personalize their services to individual customers, such as through targeted promotions and personalized assortments and pricing. As a side benefit, knowledge of individual customer behavior can also help improve sales forecasting. But in order to develop consumer-targeted strategies, we first need a demand forecasting model that captures “trends” between customers (or groups of customers). Using customers’ purchase information, we have developed a machine learning algorithm that incorporates potential trends between groups of customers based on their transaction history. Unlike previous models, this model can even estimate customer demand with transaction data alone. This personalized forecasting also allows us to optimize targeted promotions to improve profits.
     
    2019 MIT Innovations in Management Conference

    Georgia Perakis - 2016-Consumer-Dynamics-Conf

    December 14, 2016Conference Video Duration: 47:43

    Increasing Profits: Leveraging Consumer Behavior to Optimize Promotions

    Retailers know it is crucial to optimize the timing and promotion of sales to maximize profit. But how do you process the large amounts of data necessary to determine optimal pricing and timing? Left to the intuition of product managers, retailers risk missing out, but a new method created by Georgia Perakis and her team of PhD students in collaboration with Oracle RGBU, aims to change that. Using models that analyze price effects, promotion effects, and general consumer behavior data, this approach has the potential to help retailers increase their profits by an average of 3-10 percent. In a world of slim profit margins and ever-increasing competition, this could be a game changer for retailers in any industry.

    2016 MIT Consumer Dynamics Conference