Feedback regarding:

Note: comment here is limited to 140 characters. To comment at length, please email us at mediateam@colorado.edu.

Your feedback has been posted and will be replied to. Thanks for taking the time to comment.

Michele Samorani

Ph.D. Student

Biography

Michele Samorani is a fifth-year doctoral student in Operations and Information Management at the Leeds School of Business. Before joining the program, he earned a Bachelors and a Masters degree in Computer Science from University of Bologna.

Michele’s research focuses on the use of business intelligence and data mining techniques to improve business processes in health care. In his dissertation, these techniques are used to improve the drug discovery process of a pharmaceutical company, the appointment scheduling of an outpatient mental health clinic, and the real-time decision making of outpatient clinics. His work on drug discovery won the INFORMS Data Mining Best Student Paper Award in 2009.

His research is published (or accepted for publication) in Decision Support Systems and INFORMS Journal on Computing.

Publications

Article

Classification by Vertical and Cutting Multi-Hyperplane Decision Tree Induction

June 2010

Authors: Marco Better, Fred Glover, and Michele Samorani

Two-group classification is a key task in decision making and data mining applications. We introduce two new mixed integer programming formulations that make use of multiple separating hyperplanes.

Read/Download


Article

A Randomized Exhaustive Propositionalization Approach for Molecule Classification

May 2010

Author: Michele Samorani, Manuel Laguna, et al.

This work extends the propositionalization approach recently proposed for multi-relational data mining in two ways: it generates expressive attributes exhaustively and it uses randomization to sample a limited set of complex (“deep”) attributes.

Read/Download


Article

Data Mining Driven Neighborhood Search

January 2011

Author: Michele Samorani and Manuel Laguna

Metaheuristic approaches based on neighborhood search escape local optimality by applying predefined rules and constraints, such as tabu restrictions (in tabu search), acceptance criteria (in simulated annealing), and shaking (in VNS).

Read/Download