Risky Business: Predicting Cancellations in Imbalanced Multi-Classification Settings

Meena Kewlani

Purdue University

Meena is a data driven decision facilitator who enjoys employing analytics and machine learning techniques to turn data into actionable business insights. Pursuing her masters in 'Business Analytics and Information Management’ from Purdue University, she specializes in Data mining and Visualization, Statistical and Predictive Analytics, Supervised and Unsupervised Machine Learning. Prior to joining Purdue, she worked in financial software development industry as a Programmer Analyst, leveraging Agile methodologies at distinct phases of SDLC from Systems Analysis, Requirement Analysis, Programming and testing to Deployment, Maintenance and Product support. 

Abstract

We identify a rare event of a customer reneging on a signed agreement, which is akin to problems such as fraud detection, diagnosis of rare diseases, etc. where there is a high cost of misclassification. Our approach can be... [ view full abstract ]

Authors

  1. Meena Kewlani (Purdue University)
  2. Yash Ambegaokar (Purdue University)
  3. Anand Deshmukh (Purdue University)
  4. Matthew Lanham (Purdue University)

Topic Area

Topics: Topic #1

Session

SPP-3 » Student Presentations & Posters (13:30 - Friday, 13th April, Haymarket Station B)

Paper

MWDSI_Paper__final_submission.pdf

Presentation Files

The presenter has not uploaded any presentation files.