Tehran Institute for Advanced Studies (TEIAS)

/ Customer Churn Prediction through Natural Language Processing


Customer Churn Prediction
Through Natural Language Processing

May 21, 2020
(1 khordad, 1399)


This Talk is online


Dr. Hadi Amiri

Assistant Professor in the Department of Computer Science at the University of Massachusetts (UMASS)


User Generated Content (UGC), which can range from social media discussions to product reviews to private physician notes, present naturally occurring data that can be used to develop large-scale machine learning algorithms for effective processing of human language. In this talk, I will present directions toward building linguistically-aware and cognitively-motivated algorithms for prototypical problems that arise in the context of Business Intelligence. In particular, I will focus on the problem of Churn Prediction in social media which aims to identify customers who are at the high risk of leaving a given brand. I present an effective neural model for this task and, if time permits, I will discuss novel training paradigms for these type of machine learning models. I will conclude by discussing future directions of my research.


Hadi Amiri is an Assistant Professor in the Department of Computer Science at the University of Massachusetts (UMASS), Lowell. He also holds an Assistant Professor (Adjunct) appointment at Harvard University, where he is affiliated with the Department of Biomedical Informatics. Prior to joining UMASS, he completed his Postdoctoral fellowships at Harvard University and the University of Maryland, College Park. He received his Ph.D. in Computer Science from the National University of Singapore and his M.Eng. in Electrical and Computer Engineering from the University of Tehran, Iran. His primary research interests are in the areas of Natural Language Processing and Machine Learning with applications to Biomedical
Informatics and Business Intelligence.