scholarly journals Towards reliable prediction of academic performance of architecture students using data mining techniques

2018 ◽  
Vol 16 (3) ◽  
pp. 385-397 ◽  
Author(s):  
Ralph Olusola Aluko ◽  
Emmanuel Itodo Daniel ◽  
Olalekan Shamsideen Oshodi ◽  
Clinton Ohis Aigbavboa ◽  
Abiodun Olatunji Abisuga
Keyword(s):  
Data Mining ◽  
Academic Achievement ◽  
Logistic Regression ◽  
Academic Performance ◽  
Predictive Accuracy ◽  
Support Vector ◽  
Content Type ◽  
Data Mining Techniques ◽  
Svm Model ◽  
Using Data

Purpose In recent years, there has been a tremendous increase in the number of applicants seeking placements in undergraduate architecture programs. It is important during the selection phase of admission at universities to identify new intakes who possess the capability to succeed. Admission variable (i.e. prior academic achievement) is one of the most important criteria considered during the selection process. This paper aims to investigates the efficacy of using data mining techniques to predict the academic performance of architecture students based on information contained in prior academic achievement. Design/methodology/approach The input variables, i.e. prior academic achievement, were extracted from students’ academic records. Logistic regression and support vector machine (SVM) are the data mining techniques adopted in this study. The collected data were divided into two parts. The first part was used for training the model, while the other part was used to evaluate the predictive accuracy of the developed models. Findings The results revealed that SVM model outperformed the logistic regression model in terms of accuracy. Taken together, it is evident that prior academic achievement is a good predictor of academic performance of architecture students. Research limitations/implications Although the factors affecting academic performance of students are numerous, the present study focuses on the effect of prior academic achievement on academic performance of architecture students. Originality/value The developed SVM model can be used as a decision-making tool for selecting new intakes into the architecture program at Nigerian universities.

Using educational data mining techniques to increase the prediction accuracy of student academic performance

2019 ◽  
Vol 120 (7/8) ◽  
pp. 451-467 ◽  
Author(s):  
Gomathy Ramaswami ◽  
Teo Susnjak ◽  
Anuradha Mathrani ◽  
James Lim ◽  
Pablo Garcia
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Random Forest ◽  
Predictive Accuracy ◽  
Process Mining ◽  
Educational Data Mining ◽  
Content Type ◽  
Student Activities ◽  
Data Mining Techniques ◽  
Student Academic Performance

Purpose This paper aims to evaluate educational data mining methods to increase the predictive accuracy of student academic performance for a university course setting. Student engagement data collected in real time and over self-paced activities assisted this investigation. Design/methodology/approach Classification data mining techniques have been adapted to predict students’ academic performance. Four algorithms, Naïve Bayes, Logistic Regression, k-Nearest Neighbour and Random Forest, were used to generate predictive models. Process mining features have also been integrated to determine their effectiveness in improving the accuracy of predictions. Findings The results show that when general features derived from student activities are combined with process mining features, there is some improvement in the accuracy of the predictions. Of the four algorithms, the study finds Random Forest to be more accurate than the other three algorithms in a statistically significant way. The validation of the best-known classifier model is then tested by predicting students’ final-year academic performance for the subsequent year. Research limitations/implications The present study was limited to datasets gathered over one semester and for one course. The outcomes would be more promising if the dataset comprised more courses. Moreover, the addition of demographic information could have provided further representations of students’ performance. Future work will address some of these limitations. Originality/value The model developed from this research can provide value to institutions in making process- and data-driven predictions on students’ academic performances.

The Spinning Quality Control Management Based on Decision Making by Data Mining Techniques

2018 ◽  
Vol 7 (1) ◽  
pp. 72
Author(s):  
Khalid AA Abakar ◽  
Chongwen Yu
Keyword(s):  
Data Mining ◽  
Kernel Functions ◽  
Support Vector ◽  
Ann Model ◽  
Data Mining Techniques ◽  
Yarn Quality ◽  
Yarn Properties ◽  
Svm Model ◽  
Rbf Kernel

This work demonstrated the possibility of using the data mining techniques such as artificial neural networks (ANN) and support vector machine (SVM) based model to predict the quality of the spinning yarn parameters. Three different kernel functions were used as SVM kernel functions which are Polynomial and Radial Basis Function (RBF) and Pearson VII Function-based Universal Kernel (PUK) and ANN model were used as data mining techniques to predict yarn properties. In this paper, it was found that the SVM model based on Person VII kernel function (PUK) have the same performance in prediction of spinning yarn quality in comparison with SVM based RBF kernel. The comparison with the ANN model showed that the two SVM models give a better prediction performance than an ANN model.

Data mining techniques for predicting the financial performance of Islamic banking in Indonesia

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mohammed Ayoub Ledhem
Keyword(s):  
Data Mining ◽  
Financial Performance ◽  
Banking Sector ◽  
Capital Adequacy ◽  
Future Research ◽  
Islamic Banking ◽  
Accuracy Score ◽  
Content Type ◽  
Data Mining Techniques ◽  
Using Data

Purpose The purpose of this paper is to apply various data mining techniques for predicting the financial performance of Islamic banking in Indonesia through the main exogenous determinants of profitability by choosing the best data mining technique based on the criteria of the highest accuracy score of testing and training. Design/methodology/approach This paper used data mining techniques to predict the financial performance of Islamic banking by applying all of LASSO regression, random forest (RF), artificial neural networks and k-nearest neighbor (KNN) over monthly data sets of all the full-fledged Islamic banks working in Indonesia from January 2011 until March 2020. This study used return on assets as a real measurement of financial performance, whereas the capital adequacy ratio, asset quality and liquidity management were used as exogenous determinants of financial performance. Findings The experimental results showed that the optimal task for predicting the financial performance of Islamic banking in Indonesia is the KNN technique, which affords the best-predicting accuracy, and gives the optimal knowledge from the financial performance of Islamic banking determinants in Indonesia. As well, the RF provides closer values to the optimal accuracy of the KNN, which makes it another robust technique in predicting the financial performance of Islamic banking. Research limitations/implications This paper restricted modeling the financial performance of Islamic banking to profitability through the main determinants of return of assets in Indonesia. Future research could consider enlarging the modeling of financial performance using other models such as CAMELS and Z-Score to predict the financial performance of Islamic banking under data mining techniques. Practical implications Owing to the lack of using data mining techniques in the Islamic banking sector, this paper would fill the literature gap by providing new effective techniques for predicting financial performance in the Islamic banking sector using data mining approaches, which can be efficient tools in business and management modeling for financial researchers and decision-makers in the Islamic banking sector. Originality/value According to the author’s knowledge, this paper is the first that provides data mining techniques for predicting the financial performance of the Islamic banking sector in Indonesia.

Who creates value in a user innovation community? A case study of MyStarbucksIdea.com

2016 ◽  
Vol 40 (2) ◽  
pp. 170-186 ◽  
Author(s):  
Hanjun Lee ◽  
Yongmoo Suh
Keyword(s):  
Data Mining ◽  
Sentiment Analysis ◽  
Open Innovation ◽  
Information Overload ◽  
Classification Models ◽  
Content Type ◽  
Data Mining Techniques ◽  
Using Data ◽  
Basic Features ◽  
Innovation Community

Purpose – Successful open innovation requires that many ideas be posted by a number of users and that the posted ideas be evaluated to find ideas of high quality. As such, successful open innovation community would have inherently information overload problem. The purpose of this paper is to mitigate the information problem by identifying potential idea launchers, so that they can pay attention to their ideas. Design/methodology/approach – This research chose MyStarbucksIdea.com as a target innovation community where users freely share their ideas and comments. We extracted basic features from idea, comment and user information and added further features obtained from sentiment analysis on ideas and comments. Those features are used to develop classification models to identify potential idea launchers, using data mining techniques such as artificial neural network, decision tree and Bayesian network. Findings – The results show that the number of ideas posted and the number of comments posted are the most significant among the features. And most of comment-related sentiment features found to be meaningful, while most of idea-related sentiment features are not in the prediction of idea launchers. In addition, this study show classification rules for the identification of potential idea launchers. Originality/value – This study dealt with information overload problem in an open innovation context. A large volume of textual customer contents from an innovation community were examined and classification models to mitigate the problem were proposed using sentiment analysis and data mining techniques. Experimental results show that the proposed classification models can help the firm identify potential idea launchers for its efficient business innovation.

scholarly journals An Analysis on Student Academic Performance by Using Decision Tree Models

2018 ◽  
pp. 615-620
Author(s):  
Jastini Mohd. Jamil ◽  
Nurul Farahin Mohd Pauzi ◽  
Izwan Nizal Mohd. Shahara Nee
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Decision Tree ◽  
Large Volume ◽  
Educational Data Mining ◽  
Data Mining Techniques ◽  
Student Academic Performance ◽  
Tree Models ◽  
Student’S Performance ◽  
Using Data

Large volume of educational data has led to more challenging in predicting student’s performance. In Malaysia currently, study about the performance of students in Malaysia institutions is very little being addressed. The previous studies are still insufficient to identify what factors contribute to student’s achievements and lack of investigations on exploring pattern of student’s behaviour that affecting their academic performance within Malaysia context. Therefore, predicting student’s academic performance by using decision trees is proposed to improve student’s achievements more effectively. The main objective of this paper is to provide an overview on predicting student’s academic performance using by using data mining techniques. This paper also focuses on identifying the pattern of student’s behaviour and the most important attributes that impact to the student’s achievement. By using educational data mining techniques, the students, lecturers and academic institution are able to have a better understanding on the student’s achievement.

scholarly journals Prediction of active debt in the State of Pernambuco, Brazil

2020 ◽  
Vol 5 (1) ◽  
pp. 88-95
Author(s):  
Álvaro Farias Pinheiro ◽  
João Alberto Da Silva Amaral ◽  
Geraldo Torres Galindo Neto ◽  
José Nilo Martins Sampaio ◽  
Wedson Lino Soares
Keyword(s):  
Data Mining ◽  
Support Vector Machine ◽  
Logistic Regression ◽  
Random Forest ◽  
Decision Tree ◽  
The State ◽  
Support Vector ◽  
Data Mining Techniques ◽  
Collection Process ◽  
Mining Model

Application of data mining (DM) techniques to optimize the process of collection of Active Debt (AD) of the State of Pernambuco, Brazil. We apply the following data mining techniques: Decision Tree (DT), Logistic regression (LR), Nayve bayes (NB), Support vector machine (SVM), also applied to the Random Forest technique which is considered an essemble method. We observed that the RF technique obtained better results than all the techniques of classification, reaching higher values in all metrics analyzed. We note that the creation of a data mining model to choose which debts can succeed in the collection process can bring benefits to the pernambuco government. With the application of RF technique, we obtained indexes above 85% in the evaluation of the metrics.

Sign in / Sign up

Export Citation Format

Share Document