Seminars

Improving Environment, Health and Safety in Supply Chains: Some Preliminary Studies

Informations Systems and Operations Management

Speaker: Christopher S. Tang
Carter Professor of Business Administration, , UCLA Anderson School

17 March 2017 - Room Bernard Ramanantsoa - From 11:00 am to 12:30 pm


Many factories in developing countries have serious Environment, Health and Safety (EHS) issues. Due to inconsistent law enforcement, limited progress has been made. What can be done? This is an open research topic that operations management and supply chain researchers should explore. I plan to share some of my preliminary studies in this presentation.

Consumer Choice Under Limited Attention and Implications on Firm Decisions

Informations Systems and Operations Management

Speaker: Tamer Boyaci
Professor of Management Science, the Michael Diekmann Chair in Management Science, and Director of Research, , ESMT Berlin

3 March 2017 - Room Bernard Ramanantsoa - From 11:00 am to 12:30 pm


Facing an abundance of product choices and related information, but with only limited time and attention to evaluate them, consumers have to come to grips with how much and what type of information to pay attention to (and what to ignore), and make product choice and purchase decisions based on this partial information.
Evidently, it is often times easier to obtain information about some products then others (by the very nature of the product or simply because it is offered in an assortment and readily observable, among other reasons). At the same time there may be similarities (i.e., correlations) among products such that as the customer learns about a particular product, he/she may do so about another one.

Utilizing rational inattention theory, we present a general discrete choice model that describes the choice behavior of customers who optimally acquire information about available options with ex-ante uncertain values through potentially different channels with different costs. Customers trade-off the benefits of better information obtained by asking questions (and receiving informative signals) with the associated cost. We quantify acquired information and its cost through a novel function based on (Shannon) mutual information. Solving the consumer’s choice problem, we analytically characterize the resulting optimal choice behaviour. Some special cases of this model (including the generalized multinomial choice) are analyzed to illustrate key properties.

We then turn our attention to the applications of this choice model to business operations. We study assortment decisions of a seller as well as pricing decisions, demonstrating the implications of salient factors such as limited attention, cost of information, and correlations among products. Finally, we show how limited time and attention shapes the learning behaviour of the seller and its ordering strategies in a newsvendor setting.

A Markovian Approach to Choice Modeling and Assortment Optimization

Informations Systems and Operations Management

Speaker: Antoine Desir
5th year PhD candidate - Industrial Engineering and Operations Research , (Columbia University, USA)

20 February 2017 - Room Bernard Ramanantsoa (Building V) - From 10:30 am to 12:00 pm


Which set of products should be offered to arriving consumers to maximize expected revenue? This is a core revenue management problem known as assortment optimization which applies to a wide variety of settings. Discrete choice model theory offers a way to mathematically model the substitution behavior of consumers and provide a key ingredient for this problem. Many choice models have been proposed in the literature, introducing a fundamental tradeoff between model expressiveness and computational complexity. In particular, the assortment optimization problem is notoriously hard for general choice models. In this talk, we look at a new framework which tries to strike a good balance between expressiveness and tractability. In particular, the substitution behavior of consumers is modeled as transitions in a Markov chain. By doing so, this new model helps alleviate the Independence of Irrelevant Alternatives (IIA) property, a well-known limitation of the popular multinomial logit model. Moreover, it provides a good approximation to the class of random utility models. We show that not only this model has a great predictive power, it is also tractable from a computational perspective. In particular, we give a algorithm framework to derive efficient algorithm for different variants of the assortment optimization problem.

Merchant Operations of Energy Trading Networks

Informations Systems and Operations Management

Speaker: Nicola Secomandi
Professor of Operations Management , Carnegie Mellon University, Pittsburgh

13 January 2017 - Room Bernard Ramanantsoa - From 11:00 am to 12:30 pm


This talk provides an overview of the management of the operations of merchant companies that trade energy in networks of interconnected physical assets. It presents the business setting, introduces business analytics models that these firms can use to support their trading activities, and discusses modeling challenges that arise in practice, comparing different approaches from the perspective of model error. Specific examples include trading around natural gas transport and storage assets.

Revenue Management in Face of Choice Heterogeneity

Informations Systems and Operations Management

Speaker: Ali Aouad
PhD candidate at MIT

16 December 2016 - in Room Bernard Ramanantsoa (Building V) - From 10:30 am to 12:00 pm


Modern-day applications in e-commerce and brick-and-mortar retailing involve complex customer choice behaviors. Modeling this choice heterogeneity strikes a delicate balance between explaining large-scale data and prescribing efficient operational policies. At the strategic level, for the assortment selection problem, we propose a "consider-then-choose" modeling approach, borne out by the marketing literature. Experiments on a large purchase panel dataset demonstrate the strong predictive power of our models against common benchmarks. We develop a dynamic programming framework and show that many empirically vetted assumptions on how customers consider and then choose lead to tractable optimization models. Our algorithm dominates state-of-the-art commercial solvers in several regimes. Further, at the operational level, we study joint assortment and inventory management where customers show a dynamic substitution behavior. We derive the first provably good policies by revealing hidden submodular-like structure. Our approach is an order of magnitude faster than existing heuristics and increases revenue by 6% to 12% in experiments.
This work is based on several papers jointly with Profs. Vivek Farias, Retsef Levi and Danny Segev.

Contact Us  


Informations Systems and Operations Management


Campus HEC Paris
1, rue de la Libération
78351 Jouy-en-Josas cedex
France

Featured Faculty  

Dimitrios A. ANDRITSOS

Informations Systems and Operations Management (GREGHEC)

Consult résumé