Rajeev Bukralia, director of data science outreach and a lecturer in computer science for UW-Green Bay, is co-author of a chapter in the book Reshaping Society Through Analytics, Collaboration, and Decision Support, which is volume 18 in the Annals of Information Systems series published by Springer. The title of the chapter is “Using Academic Analytics to Predict Dropout Risk in E-Learning Courses.” Bukralia and co-authors Amit Deokar and Surendra Sarnikar note both the rising enrollment in online courses nationally and the higher dropout rates, arguing that early identification of at-risk students is imperative. Their study develops a model to predict real-time dropout risk for each student while an online course is being taught. The model uses 10 variables from the Student Information Systems (SIS) software and seven Course Management System (CMS) variables to establish a “dynamic risk score” with 90 percent accuracy for predicting student dropout in online courses. A full abstract is available at http://link.springer.com/chapter/10.1007/978-3-319-11575-7_6
*** *** *** *** ***
‘Things CIOs Should Know About Prescriptive Analytics’ — Rajeev Bukralia was one of several industry sources interviewed earlier this year for an article published in CIO magazine. Titled “Five Things Chief Information Officers Should Know About Prescriptive Analytics,” the article emphasized the need for data integration, speed, and continuing balance between technology-driven information and human judgment. Bukralia told writer Mary K. Pratt that organizations need to be strategic in their approach to prescriptive analytics, with collaboration among senior executives. He also added, “Prescriptive analytics isn’t about technology.” Instead, it’s about people asking the right questions and knowing how to react to the findings. Read the article.