Progress and Course Engagement (RioPACE) – Rio Salado College (LAEP Inventory)

Cloud created by:

Rebecca Ferguson
11 February 2016

Synopsis

Rio Salado College is a community college located in Arizona in the USA, which has an online enrolment of over 40,000 students. The college introduced tits Progress and Course Engagement (RioPACE) system university-wide in 2010. The system uses data modelling and predictive analytics to target interventions to low performing students.

 

The system analyses virtual learning environment (VLE) behaviours and compares students to previously successful students. Weekly warning labels are provided individually on a colour-coded traffic light system (similar to that employed by Purdue’s Course Signals). Teachers receive weekly reports on student progress and predicted completion, enabling them to target students for interventions if needed.

 

Students can also view their warning labels by accessing the RioPACE system within the VLE. Students with a yellow or red indicator are prompted to contact their module teacher for help with getting back on track.

Classification

Inventory type:

pilot

Keywords:

prediction, predictive modelling, data mining, bayesian knowledge tracing, classification

Context of Practice

Learning:

post-compulsory

Geographical:

national: USA

Pedagogic:

Rio Salado College is not explicit in its support of one pedagogic framework over another. This institutional practice relies on predictive modelling of VLE behaviours to categorise at-risk students.

Practical Matters

Tools used:

RioPACE is a custom-built system that functions within the institution’s VLE, RioLearn

Design and implementation:

RioPACE has been implemented institution-wide across all modules. The system was created by Rio Salado College. However, the college did collaborate with Purdue University and modelled its system on Purdue’s Course Signals. The college also participates in the Gates-funded WCET project as part of the Predictive Analytics Reporting (PAR) Framework.

Maturity and Evidence of Utility

Preliminary research seems to support the accuracy and validity of RioPACE’s predictive modelling. However, little to no empirical research has been published or shared in regards to increases in retention as a result of the programme’s adoption.

Further Information

Programme website: http://bit.ly/1nKnTvQ

Interview with associate dean: http://bit.ly/1ZNxs8R

 

Academic study:

Smith, V., Lange, A., & Huston, D. (2012). Predictive modelling to forecast student outcomes and drive effective interventions in online community college courses. Journal of Asynchronous Learning Networks, 16(3), 51-61.

 

See also LAEP Inventory records:

  • PAR Framework
  • Course Signals – Purdue University

Extra content

Embedded Content

Contribute

Contribute to the discussion

Please log in to post a comment. Register here if you haven't signed up yet.