You can contact Nohel Zaman at email@example.com.
Nohel Zaman is an Assistant Professor in the Department of Information Systems and Business Analytics at Loyola Marymount University. His research focuses on social media interactions of consumers. Specifically, he investigates defect existence in online reviews across multiple industries, and discovers hospital quality issues from online reviews of patients. He also focuses on identifying product safety concerns across diverse product categories. He received a Ph.D. in Business Information Technology from Virginia Tech in 2019. Additionally, he earned a B.Sc. degree in Business Administration along with a M.Sc. degree in Economics from the University of Texas at Dallas, and a M.Sc. degree in Computational Science and Engineering (concentrated in healthcare information systems) from the North Carolina A&T State University.
Virginia Tech: Ph.D., Business Information Technology 2019
North Carolina A&T State University: M.S., Computational Science and Engineering 2015
University of Texas at Dallas: M.S., Economics 2011
University of Texas at Dallas: B.S., Business Administration 2007
Areas of Expertise (2)
Healthcare Information Systems
Automated mortgage origination delay detection from textual conversationsDecision Support Systems
Arin Brahma, David M. Goldberg, Nohel Zaman, Mariano Aloiso
For modern mortgage firms, the process of setting up and verifying a new loan, known as origination, is complex and multifaceted. The literature notes that this process is rife with delays that can stunt the firm's business opportunities, but no modern analytical techniques have been developed to address the problem. In this paper, we suggest the use of text analytic and machine learning techniques to predict likely delays. In collaboration with a large national mortgage firm, we derive a large dataset of transcripts from employees' communications pertaining to potential loans. We first use information retrieval to generate an initial list of “seed terms,” or terms most associated with loans that were delayed. We then use an array of machine learning approaches to generate predictive models based upon these seed terms. We find that these approaches are comparable in performance to less interpretable state-of-the-art approaches utilizing word embeddings. The resultant models offer interpretable and high-performing solutions to mitigate the risk of delays through early risk detection.