Kaggle-in-class Data Challenges Can Boost Student Learning
Seminar/Forum
Evan Williams Theatre, Ground Floor
Peter Hall
Monash Road
Kaggle is a data modelling competition service, where participants compete to build a model with lower predictive error than other participants. Several years ago they released a reduced service that enables instructors to run competitions in a classroom setting. This paper describes the results of an experiment to determine if participating in a predictive modelling competition enhances learning.
The evidence suggests it does. In addition, students were surveyed to examine if the competition improved engagement and interest in the class.
&u=https://ms.unimelb.edu.au/events/all/learning-and-teaching/learning-and-teaching-seminar-archive/details?event=13039&picture=https://res-5.cloudinary.com/the-university-of-melbourne/image/upload/s--bFBZ1aX0--/c_fit,f_auto,h_157,w_200/v1465270928/events-uploads/image/image/23/fcqdlhh9zmylji94okjq.jpg){kind=link}
A Joint MSLC Occasional and AustMS/AMSI Teaching Seminar
(To join remotely using Zoom software go to https://unimelb.zoom.us/j/787759102)
Kaggle is a data modelling competition service, where participants compete to build a model with lower predictive error than other participants. Several years ago they released a reduced service that enables instructors to run competitions in a classroom setting. This paper describes the results of an experiment to determine if participating in a predictive modelling competition enhances learning.
The evidence suggests it does. In addition, students were surveyed to examine if the competition improved engagement and interest in the class.
Presenter
-
Dr Julia Polak, Lecturer