Data Connect: North America (Hybrid)

Join the next edition of Data Connect North America onsite in Oklahoma State University on April 26, 2023 from 6pm Onwards.

If you are interested in joining the live stream, register here.

Talk 1: Better Practices for Teaching Business Analytics & Data Science

Mainly fueled by the demand from industry, analytics and data science have emerged as new and exciting subjects for higher education institutions, helping them to become more real-world and business-need oriented by bridging the gap between academic offerings and industry demands. Teaching business analytics is a challenging endeavour for a number of reasons, including its remarkably broad scope as well as its emphasis on building both technical and behavioural/managerial skills. The challenges are especially significant when you are teaching analytics and data science in a business school to a less-technical body of students. Using visual, no-code/low-code analytics tools help mitigate the challenges in this endeavour. In this presentation, as an avid advocate for no-code/low-code analytics tools, Dr. Delen provides his reasoning and experiences in teaching analytics and data science with KNIME Analytics Platform.

Talk 2: Explainable Machine Learning for Designing Personalized Interventions: The Case of College Students Retention

With the emergence of novel methods for improving machine learning (ML) transparency, traditional decision support systems need an upgrade in their approach towards providing more actionable insights for practitioners. Particularly, given the complex decision-making process of humans, using insights obtained from group-level interpretation of ML models for designing individual interventions may lead to less than desired outcomes. Using the KNIME Analytics Platform, we demonstrate how the novel explainable ML approaches can be employed to provide actionable insights for designing personalised interventions. The demonstration is showcased in the context of college students’ attrition problem using a large and feature-rich integrated data set of freshman college students containing information about their demographics, educational, financial, and socio-economic factors.