Applying predictive analytics in identifying students at risk: A case study

Lourens, Amanda; Bleazard, David

doi:10.20853/30-2-583

Cited by 17 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Admissions data can predict the need for supporting at-risk first-year students, based on the feeder schools they attended and the marks obtained in matric. The study by Lourens and Bleazard (2016) confirmed the importance of a variety of information on background (pre-university information) in the prediction of at-risk first-year students, who need support to prevent them from dropping out by their second year. Selection data can also help understand and manage whether or not first-year students get selected for academic programmes that were their first, second or last choice.…”

Section: Recruitment and Selectionmentioning

confidence: 71%

Information ethics: From professional ethics to social ethics. How my thoughts evolved over the years – A narrative

Britz¹

2021

Information Knowledge and Technology for Development in Africa

View full text Add to dashboard Cite

Peer review declarationThe publisher (AOSIS) endorses the South African 'National Scholarly Book Publishers Forum Best Practice for Peer Review of Scholarly Books'. The manuscript was subjected to rigorous twostep peer review prior to publication, with the identities of the reviewers not revealed to the authors. The reviewers were independent of the publisher and/or authors in question. The reviewers commented positively on the scholarly merits of the manuscript and recommended that the manuscript be published. Where the reviewers recommended revision and/or improvements to the manuscript, the authors responded adequately to such recommendations. Research JustificationThis scholarly book focuses on the relationship between information knowledge and technology with regard to the Fourth Industrial Revolution. The latter is understood to be a set of highly disruptive technologies blurring the lines between the physical, digital and biological spheres, collectively referred to as cyber-physical systems. Technologies such as cognitive computing, cloud computing, the Internet of Things, big data, augmented or virtual reality, 3D systems, artificial intelligence and power supply are transforming social, economic and political systems. Ultimately, we need to transform, be more creative and innovative to develop and sustain existing and emerging capabilities in the 'new normal', which has been accidentally accelerated by COVID-19 requirements. Technologies for digital transformation create the opportunity for Africa to bypass traditional phases of industrial development as the continent has done successfully in the past. Challenges addressed in the book are inequality, social justice, ethics, access and success, policy, infrastructure and cybersecurity.The book contributes to the ongoing discourse among scholars in Africa. It consists of 10 chapters where conceptual and field research are combined. The first chapter, by Trywell Kalusopa from the University of Namibia, focuses on e-government, with an emphasis on digital government in the digital economy. The second chapter, by Kelvin J. Bwalya from the University of Johannesburg, focuses on e-government from an artificial intelligence perspective. The third chapter, by Tom Kwanya from the Technical University of Kenya, focuses on the perception of robots for information services. In the fourth chapter, Johannes Britz, from the University of Wisconsin, discusses information ethics in the digital economy. This is followed by the fifth chapter on information access and personal data by Mpho Ngoepe from the University of South Africa. The sixth chapter, by Neil D. Evans from the University of Zululand, is dedicated to e-teaching and e-learning from a Library and Information Education (LISE) perspective. In the seventh chapter, Dennis Ocholla, also from the University of Zululand, focuses on LISE in the Fourth Industrial Revolution. The eighth chapter presents Ocholla's questions on the dimensions and direction of information and knowledge management education. The ninth chapt...

show abstract

Section: Recruitment and Selectionmentioning

confidence: 71%

Information ethics: From professional ethics to social ethics. How my thoughts evolved over the years – A narrative

Britz¹

2021

Information Knowledge and Technology for Development in Africa

View full text Add to dashboard Cite

show abstract

“…A third data set (validation data) is used to provide a final estimate of the prediction model's performance or accuracy after it is implemented, preventing over-fitting in the process. 46 Every time data is utilised to train a predictive modelling technique, predictive models are produced. To put it another way, data with a strategy for predictive modelling equals a predictive model.…”

Section: Findings and Discussion Developing A Framework For The Deplo...mentioning

confidence: 99%

Developing a Framework for the Deployment of Predictive Analytics to Improve Postgraduate Student Throughputs at One Comprehensive South African University

Kariyana,

Sinkala,

Gqoli

2024

EHASS

View full text Add to dashboard Cite

There is limited understanding of the opportunities available to universities through efficient deployment of predictive analytics. This study sought to develop a framework for the successful deployment of predictive analytics at one university to ensure high-quality postgraduate throughput rates. The study adopted a systematic literature review to elicit the opportunities presented by utilising predictive analytics in decision-making to promote postgraduate student throughput rates. It emerged that literature abounds on the manner big data analytics can be used to benefit universities and students. The study argued that the traditional, non-statistical approach which has long been used to address the unsatisfactory postgraduate throughput rates has failed to yield the required outcomes. It also noted the existing effort and support mechanisms to address postgraduate student retention and throughput rates which are necessary but not sufficient. A critical recommendation is that the proffered model should not be construed as a ‘perfect and single solution’ to capsize the poor postgraduate throughput rates at the university as different limitations exist. The study concluded that there is a clear call for the need to turn the current approach to the management and promotion of postgraduate student success. As such, the opportunities available are for those institutions that are committed to improving and magnifying their future practice by making meaning of the existing large data resources at their disposal. Keywords: Framework, Higher Education Institutions, Predictive Analytics, Throughput Rates

show abstract

“…With the recent introduction of predictive and learning analytics within higher education, institutions are now seeking more nuanced data to forecast student behaviour to proactively engage students to improve student success measures (Lourens & Bleazard, 2016). For academic libraries, this new emphasis upon predictive and learning analytics represents a need to rethink how data is collected and how librarians can connect academic library outcomes to institutional outcomes such as retention and graduation (Oakleaf, 2010).…”

Section: Literature Reviewmentioning

confidence: 99%

Assessing the Impact of Reference Assistance and Library Instruction on Retention and Grades Using Student Tracking Technology

Krieb

2018

EBLIP

View full text Add to dashboard Cite

Abstract Objective – To assess the impact of community college academic librarians upon student retention and grades through reference desk visits and attendance in library instruction classes. Methods – Student ID data used for this research was collected from students that visited the reference desk to consult about a course-related question or attended a library instruction class for a specific course. After consenting to share their student ID number, the students’ IDs were scanned and uploaded to a Blackboard Analytics data warehouse. A Pyramid Analytics reporting tool was used to query and extract student-level retention and grade data based upon whether the student had visited the reference desk or attended a library instruction class. Chi-square and Fisher’s exact tests were used to discern any statistical difference in retention rates and grades between students that engaged a librarian through reference or instruction and the general student population. Results – When comparing fall-to-fall retention for all degree-seeking students, students that visited the reference desk or attended a library instruction class had a statistically higher rate of retention. When comparing fall-to-fall retention within low-retention student cohorts, students that visited the reference desk or attended a library instruction class had higher rates of retention among all low-retention cohorts. Eight of 10 cohorts were statistically higher for library instruction and 6 of 10 cohorts were statistically higher for reference visits. With respect to course grades, only 1 of 5 high enrollment courses showed a higher grade average for students that attended a library instruction class. None of the differences in average grades between students that attended a library instruction class and all students in the five courses were statistically significant. For the impact of a reference visit upon a course grade, all five courses showed a higher average grade average for students that visited the reference desk for a question related to their course than all students in the course. Four of the 5 differences were statistically significant. Conclusions – The data collected by systematically tracking students that interact with community college librarians suggests that reference desk visits and attendance of library instruction classes both have a positive, statistically significant impact upon student retention. When looking at course grades, the data does not indicate a statistically significant positive or negative impact for library instruction. The impact of visiting the reference desk upon course grades does suggest a strong, statistically significant positive correlation.

show abstract

Applying predictive analytics in identifying students at risk: A case study

Cited by 17 publications

References 16 publications

Information ethics: From professional ethics to social ethics. How my thoughts evolved over the years – A narrative

Information ethics: From professional ethics to social ethics. How my thoughts evolved over the years – A narrative

Developing a Framework for the Deployment of Predictive Analytics to Improve Postgraduate Student Throughputs at One Comprehensive South African University

Assessing the Impact of Reference Assistance and Library Instruction on Retention and Grades Using Student Tracking Technology

Contact Info

Product

Resources

About