scholarly journals Bringing Transparency to Predictive Analytics: A Systematic Comparison of Predictive Modeling Methods in Higher Education

AERA Open ◽  
2021 ◽  
Vol 7 ◽  
pp. 233285842110376
Author(s):  
Kelli A. Bird ◽  
Benjamin L. Castleman ◽  
Zachary Mabel ◽  
Yifeng Song
Keyword(s):  
Higher Education ◽  
Predictive Modeling ◽  
Predictive Analytics ◽  
Model Performance ◽  
Modeling Approaches ◽  
Predicted Probability ◽  
Institutional Researchers ◽  
Complex Models ◽  
The Stability ◽  
Additional Support

Colleges have increasingly turned to predictive analytics to target at-risk students for additional support. Most of the predictive analytic applications in higher education are proprietary, with private companies offering little transparency about their underlying models. We address this lack of transparency by systematically comparing two important dimensions: (1) different approaches to sample and variable construction and how these affect model accuracy and (2) how the selection of predictive modeling approaches, ranging from methods many institutional researchers would be familiar with to more complex machine learning methods, affects model performance and the stability of predicted scores. The relative ranking of students’ predicted probability of completing college varies substantially across modeling approaches. While we observe substantial gains in performance from models trained on a sample structured to represent the typical enrollment spells of students and with a robust set of predictors, we observe similar performance between the simplest and the most complex models.

scholarly journals The Ethics of Big Data in Higher Education

2014 ◽  
Vol 21 ◽  
pp. 3-10
Author(s):  
Jeffrey Alan Johnson
Keyword(s):  
Higher Education ◽  
Data Mining ◽  
Big Data ◽  
Student Behavior ◽  
Predictive Analytics ◽  
Scientific Basis ◽  
Social Challenges ◽  
A Value ◽  
Institutional Researchers ◽  
Potential Benefits

Data mining and predictive analytics—collectively referred to as “big data”—are increasingly used in higher education to classify students and predict student behavior. But while the potential benefits of such techniques are significant, realizing them presents a range of ethical and social challenges. The immediate challenge considers the extent to which data mining’s outcomes are themselves ethical with respect to both individuals and institutions. A deep challenge, not readily apparent to institutional researchers or administrators, considers the implications of uncritical understanding of the scientific basis of data mining. These challenges can be met by understanding data mining as part of a value-laden nexus of problems, models, and interventions; by protecting the contextual integrity of information flows; and by ensuring both the scientific and normative validity of data mining applications.

scholarly journals Remote learning among students with and without reading difficulties during the initial stages of the COVID-19 pandemic

2021 ◽  
Author(s):  
Joanna Zawadka ◽  
Aneta Miękisz ◽  
Iwona Nowakowska ◽  
Joanna Plewko ◽  
Magdalena Kochańska ◽  
...  
Keyword(s):  
Higher Education ◽  
Reading Difficulties ◽  
Learning Difficulties ◽  
Living Conditions ◽  
Demographic Information ◽  
Academic Achievements ◽  
Initial Stage ◽  
Additional Support ◽  
Academic Year ◽  
Remote Learning

AbstractThis article presents the results of a survey on yet under-researched aspects of remote learning and learning difficulties in higher education during the initial stage (March – June 2020) of the COVID-19 pandemic. A total of 2182 students from University of Warsaw in Poland completed a two-part questionnaire regarding academic achievements in the academic year 2019/2020, living conditions and stress related to learning and pandemic, as well as basic demographic information, and Dyslexia Diagnosis Questionnaire (DDQ). The analyses were carried out in three sub-groups of students: who self-reported having a formal diagnosis of dyslexia (CDYS), self-reported reading difficulties, but had no formal diagnosis of dyslexia (SIDYS), and who reported no reading difficulties (CON). The results of the survey revealed that compared with the CON group, more students from CDYS and SIDYS groups did not pass at least one exam in the summer semester. CDYS and SIDYS groups experienced higher stress due to epidemiological restrictions, they had more difficulties than CON with the organisation of learning and obtaining credit during the COVID-19 pandemic. The results indicate a need for special consideration of additional support for students experiencing reading difficulties (whether or not they have a formal diagnosis).

Abstract 223: Non-Cardiac Comorbidities in Predictive Models for Valvular Heart Disease Interventions

2016 ◽  
Vol 9 (suppl_2) ◽  
Author(s):  
Benjamin Wessler ◽  
Christine Lundquist ◽  
Gowri Raman ◽  
Jennifer Lutz ◽  
Jessica Paulus ◽  
...  
Keyword(s):  
Heart Disease ◽  
Predictive Models ◽  
Valvular Heart Disease ◽  
De Novo ◽  
Predictive Analytics ◽  
Model Performance ◽  
Median Number ◽  
Valve Surgery ◽  
Comorbid Condition ◽  
Comorbid Conditions

Background: Interventions for patients with valvular heart disease (VHD) now include both surgical and percutaneous procedures. As a result, treatments are being offered to increasingly complex patients with a significant burden of non-cardiac comorbid conditions. There is a major gap in our understanding of how various comorbidities relate to prognosis following interventions for VHD. Here we describe how comorbidities are handled in clinical predictive models for patients undergoing interventions for VHD. Methods: We queried the Tufts Predictive Analytics and Comparative Effectiveness (PACE) Clinical Prediction Model (CPM) Registry to identify de novo CPMs for patients undergoing VHD interventions. We systematically extracted information on the non-cardiac comorbidities contained in the CPMs and also measures of model performance. Results: From January 1990- May 2012 there were 12 CPMs predicting measures of morbidity or mortality for patients undergoing interventions for VHD. There were 2 CPMs predicting outcomes for isolated aortic valve replacement, 3 CPMs predicting outcomes for isolated mitral valve surgery, and 7 models predicting outcomes for a combination of valve surgery subtypes. Ten out of twelve (83%) of the CPMs for patients undergoing interventions for VHD predicted mortality. The median number of non-cardiac comorbidities included in the CPMs was 4 (range 0-7). All of the CPMs predicting mortality included at least 1 comorbid condition. The top 3 most common comorbidities included in these CPMs were, renal dysfunction (10/12, 83%), prior CVA (7/12, 58%) and measures of BMI/BSA (7/12, 58%). Diabetes was present in only 25% (3/12) of the models and chronic lung disease in only 17% (2/12). Conclusions: Non-cardiac comorbidities are frequently found in CPMs predicting morbidity and mortality following interventions for VHD. There is significant variation in the number and type of specific comorbid conditions included in these CPMs. More work is needed to understand the directionality, magnitude, and consistency of effect of these non-cardiac comorbid conditions for patients undergoing interventions for VHD.

Data Analytics and STEM Student Success: The Impact of Predictive Analytics-Informed Academic Advising Among Undeclared First-Year Engineering Students

2018 ◽  
Vol 22 (3) ◽  
pp. 497-521 ◽  
Author(s):  
Yu (April) Chen ◽  
Sylvester Upah
Keyword(s):  
Higher Education ◽  
Student Success ◽  
Academic Advising ◽  
Data Analytics ◽  
Predictive Analytics ◽  
First Year ◽  
Program Of Study ◽  
Science Technology ◽  
Mathematics Student ◽  
And Mathematics

Science, Technology, Engineering, and Mathematics student success is an important topic in higher education research. Recently, the use of data analytics in higher education administration has gain popularity. However, very few studies have examined how data analytics may influence Science, Technology, Engineering, and Mathematics student success. This study took the first step to investigate the influence of using predictive analytics on academic advising in engineering majors. Specifically, we examined the effects of predictive analytics-informed academic advising among undeclared first-year engineering student with regard to changing a major and selecting a program of study. We utilized the propensity score matching technique to compare students who received predictive analytics-informed advising with those who did not. Results indicated that students who received predictive analytics-informed advising were more likely to change a major than their counterparts. No significant effects was detected regarding selecting a program of study. Implications of the findings for policy, practice, and future research were discussed.

scholarly journals Fintech Predictive Modeling and Performance of Investment Firms in Kenya

Webology ◽  
2021 ◽  
Vol 18 (Special Issue 04) ◽  
pp. 1202-1212
Author(s):  
Elizabeth Ndichu Gitonga ◽  
Peter Wang’ombe Kariuki ◽  
Samuel Nduati Kariuki
Keyword(s):  
Predictive Modeling ◽  
Predictive Analytics ◽  
Machine Learning Techniques ◽  
Consumption Pattern ◽  
Mixed Method Research ◽  
Business Growth ◽  
Growth And Survival ◽  
Study Population ◽  
And Performance ◽  
Investment Firm

Predictive analytics is concerned with the prediction of future trends and outcomes. The approaches used to conduct predictive analytics can be classified into machine learning techniques and regression techniques. This study dteremined the influence of fintech predictive modeling on performance of investment firms in Kenya. The study population was 57 investment firms. The study employed mixed method research design by incorporating descriptive and explanatory research designs. Data was collected using questionnaires and an in-depth interview guide. Coefficient of fintech predictive modeling has a positive and significant effect on performance of investment firms. The study concluded that fintech predictive modeling allows investment firms to forecast business growth and customer behaviour chnages. It is important for an investment firm to be able to understand business growth by accurately forecasting future growth and survival. Moreover, it is of vital necessity to understand changes in customer buying/consumption behavior so as to develop products and services that suit their needs and preferences. As a result, predictive modeling is required to project future business growth and changes in customer consumption pattern.

Developing a Framework for the Effective Use of Learning Analytics

2016 ◽  
pp. 88-118
Author(s):  
Collette Gavan
Keyword(s):  
Higher Education ◽  
Decision Making ◽  
Learning Analytics ◽  
Best Practice ◽  
Predictive Analytics ◽  
Data Visualisation ◽  
The United Kingdom ◽  
Current Impact ◽  
Effective Use ◽  
Initial Framework

Research and experimentation is uncovering forms of best practice and possible factors on which to centre the analysis of students in an effective way, however learning analytics has yet to be comprehensively implemented country-wide in the United Kingdom. The chapter explores the current impact of learning analytics in higher education at mome discusses and observes the current vacancies with which a framework enabled to function with data visualisation could be utilised. The deliverable seeks to design an initial framework that has the potential to be utilised in a higher education setting for more effective and insightful decision making with regards to learner retention and engagement. This framework will combine the theory and scientific action of predictive analytics with a comparison of the most suitable data visualisation toolsets that are currently available in open-source software.

Intrinsic Defects in GaAs - the Case of El2

1987 ◽  
Vol 104 ◽  
Author(s):  
H. J. Von Bardeleben ◽  
D. Stievemard
Keyword(s):  
Electronic Structure ◽  
Stable Configuration ◽  
Theoretical Studies ◽  
Absorption Bands ◽  
Teller Distortion ◽  
Jahn Teller ◽  
The Stability ◽  
Additional Support ◽  
Jahn Teller Distortion ◽  
Experimental And Theoretical Studies

ABSTRACTThe arsenic antisite-arsenic interstitial pair model for the stable configuration of the EL2 defect in GaAs has stimulated new experimental and theoretical studies, the results of which lead to additional support for this model. Recent theoretical studies, taking into account the effect of a Jahn Teller distortion of the T2 Asi levels have given an insight into the stability and the electronic structure of the defect pair. Further, ODENDOR studies have directly confirmed this model and allowed one to specify the lattice location and the charge state of the Asi ion. The pair structure of this defect implies a reconsideration of the charge states of the EL2 defect, as well as the origin of the optical absorption bands for which transitions on the Asi ion and intracenter bands have also to be considered. The model leads further to a description of the metastable configuration : an arsenic molecule at the gallium vacancy site, the electronic structure of which is calculated. The vacancy related defects, known from electron irradiation studies, are not detected in LEC grown GaAs as native defects.

Dynamics simulation studies on the electric city car with an electromechanical differential and the rear wheels drive

2013 ◽  
Vol 61 (3) ◽  
pp. 661-673 ◽  
Author(s):  
M. Kozłowski ◽  
W. Choromański
Keyword(s):  
System Modeling ◽  
Front Axle ◽  
Dynamics Simulation ◽  
Velocity Control ◽  
Human Element ◽  
Electric Car ◽  
Electric Structure ◽  
Complex Models ◽  
The Stability ◽  
Wire System

Abstract Here we present one of the more complex models for studying the stability of driving an electric car with electromechanical differential systems. The purpose of simulation is to choose a structure of the control system for a velocity control on driven wheels (an algorithm of a differential) most appropriate for the driver. This type of goal is particularly important in the case of a disabled driver sitting in a wheelchair. The modeling takes into account both the mechanical and electric structure of the vehicle, and finally the human element - a simple model of human impact on the steer by a wire system. Modeling and simulation have used MBS package (SimMechanics). The results of the simulation have showed the best algorithms of an electromechanical differential for the velocity control of rear drive wheels: with setting a velocity difference or with an average velocity controller in the point A of the centre of a car front axle.

Sign in / Sign up

Export Citation Format

Share Document