Search results

1 – 10 of 35
Article
Publication date: 30 November 2004

S B Kotsiantis and P E Pintelas

Machine Learning algorithms fed with data sets which include information such as attendance data, test scores and other student information can provide tutors with…

Abstract

Machine Learning algorithms fed with data sets which include information such as attendance data, test scores and other student information can provide tutors with powerful tools for decision‐making. Until now, much of the research has been limited to the relation between single variables and student performance. Combining multiple variables as possible predictors of dropout has generally been overlooked. The aim of this work is to present a high level architecture and a case study for a prototype machine learning tool which can automatically recognize dropout‐prone students in university level distance learning classes. Tracking student progress is a time‐consuming job which can be handled automatically by such a tool. While the tutors will still have an essential role in monitoring and evaluating student progress, the tool can compile the data required for reasonable and efficient monitoring. What is more, the application of the tool is not restricted to predicting drop‐out prone students: it can be also used for the prediction of students’ marks, for the prediction of how many students will submit a written assignment, etc. It can also help tutors explore data and build models for prediction, forecasting and classification. Finally, the underlying architecture is independent of the data set and as such it can be used to develop other similar tools

Details

Interactive Technology and Smart Education, vol. 1 no. 4
Type: Research Article
ISSN: 1741-5659

Keywords

Article
Publication date: 25 September 2007

Joanna Jedrzejowicz and Jakub Neumann

This paper seeks to describe XML technologies and to show how they can be applied for developing web‐based courses and supporting authors who do not have much experience…

Abstract

Purpose

This paper seeks to describe XML technologies and to show how they can be applied for developing web‐based courses and supporting authors who do not have much experience with the preparation of web‐based courses.

Design/methodology/approach

When developing online courses the academic staff has to address the following problem – how to keep pace with the ever‐changing technology. Using XML technologies helps to develop a learning environment which can be useful for academics when designing web‐based courses, preparing the materials and then reusing them.

Findings

The paper discusses the benefits of using XML for developing computer‐based courses. The task of introducing new versions of existing courses can be reduced to editing appropriate XML files without any need for program change and an author can perform this task easily from a computer connected to the internet. What is more – using XML makes it possible to reuse data in different teaching situations.

Research limitations/implications

The environment has only been used for two years and further research is needed on how user‐friendly the system really is and how it can still be improved.

Practical implications

The paper describes the environment which can be used to develop and reuse online materials, courses, metadata etc.

Originality/value

The paper offers practical help to academics interested in web‐based teaching.

Details

Interactive Technology and Smart Education, vol. 4 no. 2
Type: Research Article
ISSN: 1741-5659

Keywords

Article
Publication date: 5 February 2018

Olugbenga Wilson Adejo and Thomas Connolly

The purpose of this paper is to empirically investigate and compare the use of multiple data sources, different classifiers and ensembles of classifiers technique in…

1014

Abstract

Purpose

The purpose of this paper is to empirically investigate and compare the use of multiple data sources, different classifiers and ensembles of classifiers technique in predicting student academic performance. The study will compare the performance and efficiency of ensemble techniques that make use of different combination of data sources with that of base classifiers with single data source.

Design/methodology/approach

Using a quantitative research methodology, data samples of 141 learners enrolled in the University of the West of Scotland were extracted from the institution’s databases and also collected through survey questionnaire. The research focused on three data sources: student record system, learning management system and survey, and also used three state-of-art data mining classifiers, namely, decision tree, artificial neural network and support vector machine for the modeling. In addition, the ensembles of these base classifiers were used in the student performance prediction and the performances of the seven different models developed were compared using six different evaluation metrics.

Findings

The results show that the approach of using multiple data sources along with heterogeneous ensemble techniques is very efficient and accurate in prediction of student performance as well as help in proper identification of student at risk of attrition.

Practical implications

The approach proposed in this study will help the educational administrators and policy makers working within educational sector in the development of new policies and curriculum on higher education that are relevant to student retention. In addition, the general implications of this research to practice is its ability to accurately help in early identification of students at risk of dropping out of HE from the combination of data sources so that necessary support and intervention can be provided.

Originality/value

The research empirically investigated and compared the performance accuracy and efficiency of single classifiers and ensemble of classifiers that make use of single and multiple data sources. The study has developed a novel hybrid model that can be used for predicting student performance that is high in accuracy and efficient in performance. Generally, this research study advances the understanding of the application of ensemble techniques to predicting student performance using learner data and has successfully addressed these fundamental questions: What combination of variables will accurately predict student academic performance? What is the potential of the use of stacking ensemble techniques in accurately predicting student academic performance?

Details

Journal of Applied Research in Higher Education, vol. 10 no. 1
Type: Research Article
ISSN: 2050-7003

Keywords

Article
Publication date: 14 May 2020

Byungdae An and Yongmoo Suh

Financial statement fraud (FSF) committed by companies implies the current status of the companies may not be healthy. As such, it is important to detect FSF, since such…

Abstract

Purpose

Financial statement fraud (FSF) committed by companies implies the current status of the companies may not be healthy. As such, it is important to detect FSF, since such companies tend to conceal bad information, which causes a great loss to various stakeholders. Thus, the objective of the paper is to propose a novel approach to building a classification model to identify FSF, which shows high classification performance and from which human-readable rules are extracted to explain why a company is likely to commit FSF.

Design/methodology/approach

Having prepared multiple sub-datasets to cope with class imbalance problem, we build a set of decision trees for each sub-dataset; select a subset of the set as a model for the sub-dataset by removing the tree, each of whose performance is less than the average accuracy of all trees in the set; and then select one such model which shows the best accuracy among the models. We call the resulting model MRF (Modified Random Forest). Given a new instance, we extract rules from the MRF model to explain whether the company corresponding to the new instance is likely to commit FSF or not.

Findings

Experimental results show that MRF classifier outperformed the benchmark models. The results also revealed that all the variables related to profit belong to the set of the most important indicators to FSF and that two new variables related to gross profit which were unapprised in previous studies on FSF were identified.

Originality/value

This study proposed a method of building a classification model which shows the outstanding performance and provides decision rules that can be used to explain the classification results. In addition, a new way to resolve the class imbalance problem was suggested in this paper.

Details

Data Technologies and Applications, vol. 54 no. 2
Type: Research Article
ISSN: 2514-9288

Keywords

Article
Publication date: 3 August 2022

Li Li, Hsin-Hung Wu, Chih-Hsuan Huang, Yuanyang Zou and Xiao Ya Li

Understanding the antecedents of patient safety culture among medical staff is essential if hospital managers are to promote explicit patient safety policies and…

Abstract

Purpose

Understanding the antecedents of patient safety culture among medical staff is essential if hospital managers are to promote explicit patient safety policies and strategies. The factors that influence patient safety culture have received little attention. The authors aim to investigate the antecedents of patient safety culture (safety climate) in relation to medical staff to develop a comprehensive approach to improve patient safety and the quality of medical care in China.

Design/methodology/approach

The Chinese version of the Safety Attitudes Questionnaire (CSAQ) was used to examine the attitudes toward patient safety among physicians and nurses. This medical staff was asked to submit the intra-organizational online survey via email. A total of 1780 questionnaires were issued. The final useable questionnaires were 256, yielding a response rate of 14.38%. One-way analysis of variance (ANOVA) was employed to test if different sex, supervisor/manager, age, working experience, and education result in different perceptions. Confirmatory factor analysis (CFA) was used to verify the structure of the data. Then linear regression with forward selection was performed to obtain the essential dimension(s) that affect the safety culture (safety climate).

Findings

The CFA results showed that 26 CSAQ items measured 6 safety-related dimensions. The linear regression results indicated that working conditions, teamwork climate, and job satisfaction had significant positive effects on safety culture (safety climate).

Practical implications

Hospital managers should put increased effort into essential elements of patient-oriented safety culture, such as working conditions, teamwork climate, and job satisfaction to develop appropriate avenues to improve the quality of delivered medical services as well as the safety of patients.

Originality/value

This study focused on the contribution that the antecedents of patient safety culture (safety climate) make with reference to the perspective of medical staff in a tertiary hospital in China.

Details

The TQM Journal, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 1754-2731

Keywords

Article
Publication date: 16 March 2010

Cataldo Zuccaro

The purpose of this paper is to discuss and assess the structural characteristics (conceptual utility) of the most popular classification and predictive techniques…

1924

Abstract

Purpose

The purpose of this paper is to discuss and assess the structural characteristics (conceptual utility) of the most popular classification and predictive techniques employed in customer relationship management and customer scoring and to evaluate their classification and predictive precision.

Design/methodology/approach

A sample of customers' credit rating and socio‐demographic profiles are employed to evaluate the analytic and classification properties of discriminant analysis, binary logistic regression, artificial neural networks, C5 algorithm, and regression trees employing Chi‐squared Automatic Interaction Detector (CHAID).

Findings

With regards to interpretability and the conceptual utility of the parameters generated by the five techniques, logistic regression provides easily interpretable parameters through its logit. The logits can be interpreted in the same way as regression slopes. In addition, the logits can be converted to odds providing a common sense evaluation of the relative importance of each independent variable. Finally, the technique provides robust statistical tests to evaluate the model parameters. Finally, both CHAID and the C5 algorithm provide visual tools (regression tree) and semantic rules (rule set for classification) to facilitate the interpretation of the model parameters. These can be highly desirable properties when the researcher attempts to explain the conceptual and operational foundations of the model.

Originality/value

Most treatments of complex classification procedures have been undertaken idiosyncratically, that is, evaluating only one technique. This paper evaluates and compares the conceptual utility and predictive precision of five different classification techniques on a moderate sample size and provides clear guidelines in technique selection when undertaking customer scoring and classification.

Details

Journal of Modelling in Management, vol. 5 no. 1
Type: Research Article
ISSN: 1746-5664

Keywords

Open Access
Article
Publication date: 9 July 2020

Aminudin Zuhairi, Amy Ching Tsu Hsueh and I-Chin Nonie Chiang

This research attempts to reveal ways of addressing challenges in open universities related to empowering lifelong learning; establishing policies and strategies in…

1886

Abstract

Purpose

This research attempts to reveal ways of addressing challenges in open universities related to empowering lifelong learning; establishing policies and strategies in dropouts, student portfolio and support services for students with special needs; and implementing online instructional design and strategies. Two institutions were investigated, namely National Open University (NOU) Taiwan and Universitas Terbuka (UT) Indonesia, both founded in the 1980s to serve lifelong learners with diverse backgrounds and needs. This study was aimed at understanding good practices and challenges for improvement for the two open universities in those areas being investigated.

Design/methodology/approach

This research was qualitative using document analysis along with focus group discussions and interviews with administrators, academic staff, students and alumni to collect data for analysis.

Findings

Lifelong learning is the necessity of individual in societies for continuing professional development through enabling access to quality university education. Open universities have been tasked to cater for lifelong learners using non-traditional approaches, new technology and adapting to online learning and teaching in digital age. This research was exploratory, and the findings were expected to improve understanding of lifelong learning in open universities, particularly in NOU and UT.

Practical implications

Findings of this research are relevant to open universities to enhance its missions and define its possible new roles to serve lifelong learners.

Originality/value

This research reveals the roles of open universities in lifelong learning and enhances understanding of open universities that have a wide range of responsibilities in offering programs and courses to accommodate lifelong learners.

Details

Asian Association of Open Universities Journal, vol. 15 no. 2
Type: Research Article
ISSN: 1858-3431

Keywords

Open Access
Article
Publication date: 10 December 2019

Aminudin Zuhairi, Navaratnasamy Karthikeyan and Saman Thushara Priyadarshana

The purpose of this paper is to reveal how support services for open and distance students are designed, developed and implemented to ensure successful learning to take…

9782

Abstract

Purpose

The purpose of this paper is to reveal how support services for open and distance students are designed, developed and implemented to ensure successful learning to take place, with specific references to the Open University of Sri Lanka (OUSL) and Universitas Terbuka (UT) Indonesia. Success in distance learning is one major challenge for open universities to respond to expectations of students and stakeholders. This study focuses on the strategies of student support services in OUSL and UT, investigating related factors including instructional design and development, learning engagement and motivation, policy and strategy in reducing dropouts, use of OER/MOOCs, and quality assurance.

Design/methodology/approach

A qualitative study was employed involving analyses of documents; interviews and focus group discussion with senior administrators, academic staff, students; and on-site observation in locations of teaching and learning.

Findings

This research is exploratory in nature. Findings of the study are expected to improve our understanding of student support in distance learning, in which analysis is based on good practices, challenges and rooms for improvement of both OUSL and UT.

Practical implications

Findings of this study reveal practices and lessons learnt that may be useful as reference to open universities, taking into considerations the fact that each open university has been established to address specific challenges in its own unique circumstances.

Originality/value

This research may be adopted as baseline framework for analysis of student support for open universities. Further in-depth study is needed to understand how various aspects of student support contribute to success in open and distance learning.

Details

Asian Association of Open Universities Journal, vol. 15 no. 1
Type: Research Article
ISSN: 1858-3431

Keywords

Book part
Publication date: 26 October 2017

Son Nguyen, John Quinn and Alan Olinsky

We propose an oversampling technique to increase the true positive rate (sensitivity) in classifying imbalanced datasets (i.e., those with a value for the target variable…

Abstract

We propose an oversampling technique to increase the true positive rate (sensitivity) in classifying imbalanced datasets (i.e., those with a value for the target variable that occurs with a small frequency) and hence boost the overall performance measurements such as balanced accuracy, G-mean and area under the receiver operating characteristic (ROC) curve, AUC. This oversampling method is based on the idea of applying the Synthetic Minority Oversampling Technique (SMOTE) on only a selective portion of the dataset instead of the entire dataset. We demonstrate the effectiveness of our oversampling method with four real and simulated datasets generated from three models.

Details

Advances in Business and Management Forecasting
Type: Book
ISBN: 978-1-78743-069-3

Keywords

Article
Publication date: 27 May 2021

Sara Tavassoli and Hamidreza Koosha

Customer churn prediction is one of the most well-known approaches to manage and improve customer retention. Machine learning techniques, especially classification…

Abstract

Purpose

Customer churn prediction is one of the most well-known approaches to manage and improve customer retention. Machine learning techniques, especially classification algorithms, are very popular tools to predict the churners. In this paper, three ensemble classifiers are proposed based on bagging and boosting for customer churn prediction.

Design/methodology/approach

In this paper, three ensemble classifiers are proposed based on bagging and boosting for customer churn prediction. The first classifier, which is called boosted bagging, uses boosting for each bagging sample. In this approach, before concluding the final results in a bagging algorithm, the authors try to improve the prediction by applying a boosting algorithm for each bootstrap sample. The second proposed ensemble classifier, which is called bagged bagging, combines bagging with itself. In the other words, the authors apply bagging for each sample of bagging algorithm. Finally, the third approach uses bagging of neural network with learning based on a genetic algorithm.

Findings

To examine the performance of all proposed ensemble classifiers, they are applied to two datasets. Numerical simulations illustrate that the proposed hybrid approaches outperform the simple bagging and boosting algorithms as well as base classifiers. Especially, bagged bagging provides high accuracy and precision results.

Originality/value

In this paper, three novel ensemble classifiers are proposed based on bagging and boosting for customer churn prediction. Not only the proposed approaches can be applied for customer churn prediction but also can be used for any other binary classification algorithms.

Details

Kybernetes, vol. 51 no. 3
Type: Research Article
ISSN: 0368-492X

Keywords

1 – 10 of 35