Tag Archives: predictive analytics

Type: Evidence | Proposition: A: Learning | Polarity: | Sector: | Country:

This literature paper briefly anticipates and outlines a project about integrating labour market information in a learning analytics goal-setting application, with the aim to help student to develop skills that are currently requested by the labour market.

Authors highlight the absurd contemporary trend that characterise labour market, with high levels of youth unemployment together with difficulties of companies to find candidates with the right job skills.

In the developed IT solution, abour market data will be analyzed to extract information that may impact student planning. This will lead to a "goal-setting program in which students can specify goals (e.g., learning goals as subgoals of more distant career goals)" and have access to "relevant labour market information, view progress and success indicators, and receive recommendations from course advisors".

According to authors, "this research expands the impact of learning analytics beyond the educational setting by helping students to navigate the education-to-employment pathway using a goal-setting application" characterized by analytical methods joint with an examination of learning constructs and educational theories.

Citation: V. Kobayashi, S.T. Mol, G. Kismihók (2014). Labour Market Driven Learning Analytics. Journal of Learning Analytics, 1(3), 207-210 | Url: https://epress.lib.uts.edu.au/journals/index.php/JLA/article/view/4194

Type: Evidence | Proposition: A: Learning | Polarity: | Sector: | Country:

In recent years, one of the main issues for companies in hiring new employees consists in the bridge between skills provided by HE and the ones required by a more and more fast and agile market. This is why it is particular important for students to identify as soon as possible what can be their career fields, taking into consideration natural attitudes and personal wishes.

In this scientific paper, authors describe the development of a tool, or a Portal, to improve career readiness of students during Higher Education. IT tools like this are particularly interesting, because gives to companies the potential capability to have visibility on the areas of interests of the best graduates, and contacting them soon as they finish their studies, as well as compare these attitudes with workplace results and skill improvements.

This Portal consists of three major processes:

1) Career Readiness

2) Career Prediction

3) Career Development.

Career Readiness is formed  by different software modules which allows to measure the general professional dispositions required for a successful career in the 21st Century (21st Century Skills). These professional dispositions have been divided in 6 macro-areas, which in general describe  "the natural tendencies, mind state and preparations of each individual towards a professional practice": Openness to challenge, Critical Thinking, Resilience, Learning Relationships, Responsibility for Learning, and Creativity.

Career Prediction is calculated on some indicators, which are transformed in "Raw scores", that allows to cluster individuals and compare them with the features of different Community of Practice (people who share knowledge, experiences and passion on the same set of topics).

Career Development, which allows people to join different Communities of Practice and build their career domain awareness and skills.

The  tool integrates Learning Analytics techniques for career readiness "by focusing on meta-learning dimensions that accompany formal education while positioning learners and instructors at the center of the analytics process". Learning Analytics allows to provide solutions to help learners to reflect and act upon feedback about their learning performance.  Furthermore, Learning Analytics reveals hidden patterns of common traits among learners viewed as future candidates of the job market.

Citation: AbuKhousa, E.; Atif, Y., "Big learning data analytics support for engineering career readiness," in Interactive Collaborative Learning (ICL), 2014 International Conference on , vol., no., pp.663-668, 3-6 Dec. 2014 doi: 10.1109/ICL.2014.7017849 | Url: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7017849&punumber%3D7002490%26sortType%3Dasc_p_Sequence%26filter%3DAND(p_IS_Number%3A7017737)%26pageNumber%3D4

Type: Evidence | Proposition: A: Learning | Polarity: | Sector: | Country:

This study aims to develop a recommender system for social learning platforms that combine traditional learning management systems with commercial social networks like Facebook. We therefore take into account social interactions of users to make recommendations on learning resources. We propose to make use of graph-walking methods for improving performance of the well-known baseline algorithms. We evaluate the proposed graph-based approach in terms of their F1 score, which is an effective combination of precision and recall as two fundamental metrics used in recommender systems area. The results show that the graph-based approach can help to improve performance of the baseline recommenders; particularly for rather sparse educational datasets used in this study.

Screen Shot 2015-12-04 at 12.41.06 Screen Shot 2015-12-04 at 12.41.20 Screen Shot 2015-12-04 at 12.41.32 Screen Shot 2015-12-04 at 12.41.46

Citation: Fazeli, S., Loni, B., Drachsler, H., Sloep, P. (2014, 16-19 September). Which recommender system can best fit social learning platforms? In C. Rensing, S. de Freitas, T. Ley, & P. Muñoz-Merino (Eds.), Open Learning and Teaching in Educational Communities. Proceedings of the 9th European Conference on Technology Enhanced Learning (EC-TEL2014), Lecture Notes in Computer Science 8719 (pp. 84-97). Graz, Austria: Springer International Publishing. | Url: http://hdl.handle.net/1820/5685

Type: Evidence | Proposition: C: Uptake | Polarity: | Sector: | Country:

Evidence of the month: September 2015

In these two videos

  • https://www.youtube.com/watch?v=uu9ii38TcFI
  • https://www.youtube.com/watch?v=9Z-hp5NrSBg

Tim Renick talks to a committee of the US Senate about the successful large-scale application of predictive analytics at Georgia State University. The university aims to ensure – using reliable data – that students are doing what they need to do within the context of their ability and their resources and that they are making significant progress towards their degrees.

Renick, who is Vice Provost of the university, explains that they are using data proactively, picking up on problems that are associated with low grades or student dropout. He states that this has resulted in

  • Reduction of the average time it takes students to gain a degree
  • 1700 more students graduating annually than did so five years ago
  • Elimination of achievement gaps based on race, ethnicity and economics.

The university is currently tracking 30,000 students, using predictive modeling based on ten years of data and 800 risk factors.

Students each have individual pathways, made up of a set of courses they should be taking each semester. Those who are making mistakes will find this out almost immediately, as the analytics will trigger a one-to-one meeting with an adviser. These meetings are personalized, engaging students, who get to know their support team better than was the case in the past. Early weaknesses in performance are addressed by immediate interventions, so they are removed rather than compounded.

These short videos do not set out detailed data and analysis, but they do provide evidence of analytics being rolled out at scale, and of engagement with these analytics at a national level.

Citation: 'Georgia State University - Dr. Tim Renick' (2015), YouTube, uploaded by Georgia State University | Url: https://www.youtube.com/watch?v=9Z-hp5NrSBg

Type: Evidence | Proposition: C: Uptake | Polarity: | Sector: | Country:

The paper deals with two key ideas that could help schools graduate more students on time. The first is to produce a ranked list that orders students according to their risk of not graduating on time. The second is to predict when they'll go off track, to help schools plan the urgency of the interventions. Both of these predictions are useful in identification and prioritization of students at risk and enable schools to target interventions. The eventual goal of these efforts is to focus the limited resources of schools to increase graduation rates.

The results of this study have helped a school district systematically to adjust analytical methods as they continue to build a universal EWI (early-warning indicator) system. The district is also highly interested in the web-based dashboard application that was developed.

Citation: Aguiar, Everaldo, Lakkaraju, Himabindu, Bhanpuri, Nasir, Miller, David, Yuhas, Ben, & Addison, Kecia L. (2015). Who, when, and why: a machine learning approach to prioritizing students at risk of not graduating high school on time. Paper presented at the Proceedings of the Fifth International Conference on Learning Analytics And Knowledge. | Url: http://d-miller.github.io/assets/AguiarEtAl2015.pdf