Join us in welcoming Osman Ozaltin, one of ISE’s associate professors, as he discusses industrial engineering topics. Alums and friends of the program are always welcome.
Data Science and Operations Research Methods in Health and Humanitarian Systems
In the first part of the talk, I will present a summary of my research portfolio in health and humanitarian systems engineering. The second part of the talk will focus on a recent project about detecting illicit massage businesses (IMBs) from publicly available data sources. Approximately 11,000 alleged IMBs exist across the United States hidden in plain sight among legitimate businesses. These illicit businesses frequently exploit workers, many of whom are victims of human trafficking, forced or coerced to provide commercial sex. Although IMB review boards like Rubmaps.ch can provide first-hand information to identify IMBs, these sites are likely to be closed by law enforcement. Open websites like Yelp.com provide more accessible and detailed information about a larger set of massage businesses. Reviews from these sites can be screened for risk factors of trafficking. We develop a natural language processing (NLP) approach to detect online customer reviews that indicate a massage business is likely engaged in human trafficking. Human trafficking investigators face challenges while processing the sheer volume of publicly available online data. The potential for NLP-based detection algorithms is hindered by the scarcity of large and accurately labeled training datasets. Labeling datasets related to human trafficking is difficult because identifying indicators of trafficking requires domain expertise, trafficking cases comprise a small portion of the data, and reviewing the disturbing content is emotionally demanding for individuals. Active learning optimizes model training by strategically querying the most informative data points, thereby achieving high accuracy with minimal annotations. We formulate active learning as a decision model and learn a policy through deep reinforcement learning.
Osman Özaltın is an Associate Professor in the Edward P. Fitts Department of Industrial and Systems Engineering, and a member of the Personalized Medicine Faculty Cluster at the North Carolina State University. He received his MS and PhD degrees in Industrial Engineering from the University of Pittsburgh. His dissertation received the Pristker Doctoral Dissertation Award from Institute of Industrial and Systems Engineering in 2013. His research interests span methodological, computational, and applied aspects of Operations Research and data science, focusing on decision-making problems in diverse application areas such as personalized medicine, public health, healthcare delivery and illicit supply chains. His methodological contributions pertain to advancing stochastic programming, robust optimization and bilevel programming methodologies. He is a member of Institute for Operations Research and Management Science (INFORMS) and Institute for Industrial and Systems Engineering (IISE). He serves as an Associate Editor for the IISE Transactions, INFORMS Journal on Computing, and Healthcare Management Science journals.
