What if you had a genie in a bottle who could regularly give you answers to your top 3 questions about your students, curriculum and instruction?
Pure fantasy? Not really. If you have the right data-mining techniques, you can conjure up the data genie whenever you need to answer your most pressing questions.
Data mining is the process of looking for patterns in data from different perspectives and then summarizing them into useful information. In schools, educators look for trends in their student data and then pose their most relevant questions about student learning. How do we best place students in leveled classes? Where is the math curriculum strong? Where is it weak? How are English-language learners doing in terms of individual growth, but also compared with native English-speakers? Which students exhibit sub-par growth? Who are the outliers on both ends of the spectrum and how do their standardized test scores compare with their grades?
Join educational data-mining expert Scott Genzer for a 2-hour hands-on webinar that will demonstrate data-mining techniques with sample data based on real school data sets. Via live screenshare, Scott will show you ways that school data can answer your most critical questions. You will explore several typical, yet specific, examples of educational data-mining that can help you yield better information from your own data.
- Taking an inventory of your data to determine what you can tap to answer your questions
- Preparing yourself and your data for mining: extraction, transfer, upload. How to get the data in a usable form
- What software and expertise do you need?
- Pitfalls and limitations of educational data mining: over-fitting, correlation vs. causation, absolute vs. growth data, data-driven vs. data-informed decisions, cold vs. hot data, the need to triangulate, legal and security concerns
- Discovering patterns in student data and creating student groupings with mining techniques
- How to create models that make predictions on student performance
- Mining unstructured school data (e.g. teacher comments, student portfolios, etc.)
- Best practices for using data results
- The future of data mining and predictive analytics in education