Upcoming Events

All of our events are free and open to the public. If you would like to RSVP, you can do so at cunydatamining.eventbrite.com. Alternatively, you can email us with your name, organizational affiliation (if any), and the event name(s) at datamining@gc.cuny.edu.

In Fall 2014, we will be hosting two seminars and one workshop. We will update this page systematically as we finalize time and place. Make sure to come back and check here for the most up-to-date information!

Fall 2014 Events

SEPTEMBER 18, 2014, 12 Noon @ The Graduate Center, Room 6112

Longitudinal Data Analysis in Education Decision Making

alex bowers picSpeaker: Professor Alex J. Bowers, Teachers College

Abstract: Schools are awash in data, from grades, to test scores, discipline reports, and attendance among many others. How can teachers, school leaders, policymakers, students and parents put the data that we already collect in schools to better use? This presentation will provide an overview of the emerging domain of the application of visual data analysis to longitudinal data analytics to examine overall K-12 schooling outcomes (such as high school graduation or dropping out) in an effort to help direct the limited resources of schools to specific student needs. The presentation will focus on determining empirically similar patterns of student longitudinal course grade trajectories, and how to compare so called time-nested “mixture models” with current identification practices in schools.

Bio: Alex J. Bowers is an Associate Professor of Education Leadership at Teachers College, Columbia University, where he works to help school leaders use the data that they already collect in schools in more effective ways to help direct the limited resources of schools and districts to specific student needs. His research focuses on the intersection of effective school and district leadership, data driven decision making, student grades and test scores, student persistence and dropouts. His work also considers the influence of school finance, facilities, and technology on student achievement. Dr. Bowers studies these domains through the application of Intensive Longitudinal Data analysis (ILD), such as data visualization analytics, multi-level and growth mixture modeling, and cluster analysis heatmap data dashboards. He earned his Ph.D. in K12 Educational Administration from Michigan State University, and previous to teaching and education research, spent a decade as a cancer researcher in the biotechnology industry, with an M.S. in Biochemistry, Microbiology and Molecular Biology, and a B.S. in Biochemistry.

—————————

OCTOBER 8, 2014, 12 Noon @ The Graduate Center, Room 6112

ASSISTMENTS: An educational research platform that allows randomized controlled experiments

Speaker: Professor Neil Heffernan, Worcester Polytechnic Instituteheffernan pic

Abstract: In this talk I will describe a shared scientific instrument being used by multiple universities to do cognitive science research on human learning in K-12 schools. The web-based platform is called “ASSISTments” and is used by teachers and their students for 1) nightly homework support and 2) in-class formative assessment and differentiated instruction. Our schools think of ASSISTments as a valuable free public service. For this talk, I will address the different types of ways we use ASSISTments to measure knowledge, and the different randomized controlled experiments being conducted with ASSISTments. I will give multiple examples of the different kinds of ways researchers can use this system. Currently, we have 147 randomized controlled experimenters that conduct very short (minutes-long) experiments comparing different types of feedback. I will discuss an NSF funded 8 year-long longitudinal tracking study we are doing in cooperation with Professor Ryan Baker at Teachers College. Another example I will give will be a US Dept of Ed 10 million dollar math study where, in cooperation with Jim Pellegrino and Susan Goldman at UIC, we are exploring applying cognitive science principles to improve a commonly used middle school math textbook (Connected Math). I will talk about data mining work done with ASSISTments data showing how data collected with the system yields more accurate predictions of student knowledge. I will talk about the Efficacy Trail SRI is doing to see if ASSISTments can be used to raise Smarter Balance test scores. I will also talk about joint work with Zach Pardos in which Zach won an award in the KDD Cup challenge in predicting student performance. Zach’s use of Bayes Nets to track knowledge helps us better track and report on student knowledge. Also, I will talk about the online professional development work that Gates Foundation is funding us to do as part of our plan to scale-up to 1 million children and the PD work we are doing with the ~80 teachers a week asking for accounts.   Finally I will talk about our most recent NSF grant that allows us to support researchers from across country who are proposing studies to run with our subject pool of 50,000 students.

Bio: Dr. Neil Heffernan graduated summa cum laude from Amherst College in History and Computer Science. Neil taught mathematics to eighth grade students in Baltimore City as part of Teach for America, a program that selectively recruits top candidates to teach in inner-city schools. Neil then decided to do something easier and get a PhD in building intelligent tutoring systems. Neil enrolled in Carnegie Mellon University’s Computer Science Department to do multi-disciplinary research in cognitive science and computer science to create educational software that leads to higher student achievement. For his dissertation, Neil built the first intelligent tutoring system that incorporated a model of tutorial dialog. This system was shown to lead to higher student learning, by getting students to think more deeply about problems. It is based upon detailed studies of students, which produced basic cognitive science research results on the nature of human thinking and learning. Neil is now a tenured professor at Worcester Polytechnic Institute. Neil and his colleagues are working in close collaboration with teams of teachers and graduate students to create the next generation of web-based platforms to support teachers and students. Neil’s current research uses, and builds, ASSISTments, a platform used by 50,000 students as part of their normal class work. Over 50 million problems have been solved by students, and reported to teachers. He has received awards from the Worcester Public Schools system, and the Massachusetts Association of School Committees for his work helping schools. Neil has written over 60 strictly peer-reviewed publications. He has received multiple awards from his professional associations. Since coming to WPI, Neil has received over a dozen major grants (3 from NSF including the prestigious CAREER award, 3 from the US Dept of Education, as well as grants from the Office of Naval Research, the US Army, the Massachusetts Technology Transfer Center, the Bill and Melinda Gates Foundation and the Spencer Foundation) worth over 13 million dollars. Recently, Neil’s work was cited in the National Educational Technology Plan, and featured in the NY Times Sunday Magazine. Neil helped start the WPI Learning Sciences and Technologies PhD program and has seen it grow to include three more faculty members.

—————————

NOVEMBER 6, 2014, 9 am to 3 pm @ The Graduate Center, Room 6304.01

Hands-on Data Mining Training
Mikhail Headshot

Speaker: Mikhail Golovnya, Senior Scientist at Salford Systems

Abstract: In this workshop, attendees will get step-by-step instruction for the most popular data mining techniques used in predictive analytics including decision trees, classification, segmentation, non-linear regression, ensemble methods, and boosted decision trees. Attendees will be able to walk away with everything they will need to start their own data mining projects and able to apply their new data mining knowledge at their organization to create immediate value. Additionally, all attendees receive 90-day access to the SPM Salford Predictive Modeler technology.

Agenda of event:

  • 8:30am – 9:00am – Check-in
  • 9:00am – 12:00pm – Introduction to Data Mining & Case Study Examples
  • 12:00pm – 1:00pm – Lunch (not provided)
  • 1:00pm – 3:00pm – Hands-On Technical Session

Bio: Mikhail Golovnya graduated from Kharkov State Polytechnic University, Ukraine in 1995 with a Specialist Engineering Degree in Flight Dynamics and Space Shuttle Control. In 1996, he was a Research Scholar in Econometrics and Finacnce at Saint Norbert College, Wisconsin. Golovnya later joined the Master of Science in Computation Statistics program at the University of Central Florida, Orlando from which he graduated with honors in fall of 2000. Golovnya began his work with Salford Systems as a Systems Analyst in the summer of 1999. He is primarily responsible for data mining consultation projects and works in model development and the search for technological improvements to Salford’s core products. He is also responsible for advanced of CART®, MARS®, TreeNet®, Random Forests®, and prototyping of new data mining algorithms and modeling automation. Golovnya also leads training sessions in CART, MARS, TreeNet, and Random Forests and provides guidance and technical support to Salford Systems’ data mining clients.

This event is co-sponsored by the CUNY Data Mining Initiative and the Ph. D. Program in Psychology of CUNY Graduate Center.