A Study on Students Enrollment Prediction using Data Mining

Haris, Norhaidah Abu; Abdullah, Munaisyah; Hasim, Nurdatillah; Rahman, Fauziah Abdul

doi:10.1145/2857546.2857592

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recent literature utilizes machine learning classification techniques to predict enrollment rates. Haris et al (2016) introduce the enrollment prediction process and predicted enrollment using a decision tree. Similar studies were done by Saini and Jain (2013) and Soltys et al (2021), though using a variety of machine learning methods including CART, naive Bayes, k -nearest neighbors, artificial neural networks, support vector machine, boosting, and logistic regression for enrollment rate prediction.…”

Section: Methodological Set-up and Literature Reviewmentioning

confidence: 99%

A Combinatorial Optimization Framework for Scoring Students in University Admissions

et al. 2022

View full text Add to dashboard Cite

Background and Objectives Selecting applications for college admission is critical for university operation and development. This paper leverages machine learning techniques to support enrollment management teams through data-informed decision-making in this otherwise laborious admissions processing. Research Design and Measures Two aspects of university admissions are considered. An ensemble learning approach, through the SuperLearner algorithm, is used to predict student show (yield) rate. The goal is to improve prediction accuracy to minimize over- or under-enrollment. A combinatorial optimization framework is proposed to weigh academic performance and experiential factors for ranking and selecting students for admission. This framework uses simulated annealing, and an efficacy study is presented to evaluate performance. Results The proposed framework is illustrated for selecting an incoming class by optimizing predicted graduation rate and by developing an eligibility index. Each example presents a selection process under potential academic performance and experiential factor targets a university may place on an admitted class. R code is provided for higher education researchers and practitioners to apply the proposed methods in their own settings.

show abstract

Section: Methodological Set-up and Literature Reviewmentioning

confidence: 99%

A Combinatorial Optimization Framework for Scoring Students in University Admissions

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The accuracy and performance of these prediction models are thoroughly assessed and compared. In its conclusion, the article underscores the utility of data mining for enrolment management and planning, ultimately identifying the neural network as the most effective method for predicting student enrolment (Haris et al, 2016).…”

Section: Data Mining Approachmentioning

confidence: 99%

Enhancing Business Sustainability Through Technology-Enabled AI: Forecasting Student Data and Comparing Prediction Models for Higher Education Institutions (HEIs)

Gnoh,

Keoy,

Iqbal

et al. 2024

PaperASIA

View full text Add to dashboard Cite

This study aims to enhance business sustainability in the context of Higher Education Institutions (HEIs) by utilizing AI and forecasting techniques. It explores the development and comparison of prediction models, including the use of dashboard development, to support decision-making processes within HEIs. The study covers various aspects, including the background of forecasting and prediction models, the use of specific models such as the Prophet Model, Long Short-Term Memory (LSTM) Model, and Polynomial Regression Model, as well as the importance of dashboards for HEIs. The methodology section outlines the data collection and preparation process, model selection, approach, diagrams, functional and non-functional requirements, justification of tools, and libraries and models used. The implementation section delves into the system design and development of the dashboard, including the login page, homepage, forecast page, and insert data page. As for the findings, the LSTM Model has proven to be the most accurate and suitable model to be implemented for forecasting student enrolment data in this study. The dashboard's future enhancements involve adding more faculties, predictive features for resource allocation, refining the visual identity, improving user registration on the login page, and exploring better models for student enrolment predictions. Overall, the study provides valuable insights into the application of AI and forecasting techniques in HEIs, aiming to enhance business sustainability and decision-making processes. It contributes to the growing body of knowledge on the use of technology-enabled AI in higher education institutions, with a focus on forecasting student enrolment data and developing prediction models.

show abstract

“…Perguruan tinggi yang menjadi tempat penerapan data mining sangat memperhatikan data pendaftaran mahasiswa, mencari pola dan kemungkinan pengaruhnya terhadap keputusan mahasiswa untuk masuk perguruan tinggi. Prediksi, sebagai salah satu teknik data mining yang umum digunakan dalam literatur, dianggap sebagai metode praktis untuk manajemen perguruan tinggi dalam menghasilkan pengetahuan yang akan digunakan untuk pengambilan keputusan [6].…”

Section: Pendahuluanunclassified

Comparative Analysis of Data Mining Classification Algorithm Performance for Searching Prospective Student Interests

Budiman

Niqotaini²

2022

SISTEMASI

View full text Add to dashboard Cite

Penerimaan mahasiswa baru merupakan kegiatan yang selalu dilaksanakan setiap Perguruan Tinggi dalam menyambut Tahun Akademik baru. Penurunan jumlah pendaftar pada setiap tahun terutama masa pandemi Covid-19 saat ini menjadi permasalahan AMIK HASS dalam perekrutan mahasiswa, maka diperlukan upaya untuk mengolah data penerimaan mahasiswa baru yang ada. Penerapan data mining menggunakan algoritma klasifikasi salah satunya bertujuan untuk melakukan prediksi. Algoritma klasifikasi yang digunakan yaitu Naïve Bayes (NB), Decision Tree J48 (J48), K-Nearest Neighbor (K-NN), Random Forest (RF) dan Support Vector Machine (SVM). Pengujian kelima algoritma klasifikasi bertujuan untuk menganalisis kinerja masing-masing algoritma, sehingga memberikan informasi dan pengetahuan data set sebagai rekomendasi dalam strategi promosi dimasa yang akan datang. Penelitian ini menggunakan Machine Learning Waikato Environment for Knowledge Analysis (WEKA). Data set yang digunakan dalam penelitian ini adalah penelusuran potensi dan minat calon mahasiswa baru sebanyak 5934 record. Pengujian yang dilakukan pada kelima algoritma klasifikasi menggunakan mode test percentage split yaitu 70% untuk data training dan 30% untuk data testing. Hasil pengujian menunjukkan tingkat akurasi tertinggi pada algoritma klasifikasi J48 sebesar 90,34% diikuti RF sebesar 89,04%, SVM sebesar 88,43%, K-NN sebesar 87,53%, SVM sebesar 87,25%. Berdasarkan hasil pengujian algoritma klasifikasi J48 merupakan algoritma terbaik terhadap pengujian data set dengan tingkat kesalahan prediksi paling rendah sebesar 0,26. Algoritma klasifikasi Decision Tree J48 memiliki aturan eksplisit untuk klasifikasi dan penanganan data heterogen yang tepat dengan memiliki rule sebanyak 255.

show abstract

A Study on Students Enrollment Prediction using Data Mining

Cited by 7 publications

References 9 publications

A Combinatorial Optimization Framework for Scoring Students in University Admissions

A Combinatorial Optimization Framework for Scoring Students in University Admissions

Enhancing Business Sustainability Through Technology-Enabled AI: Forecasting Student Data and Comparing Prediction Models for Higher Education Institutions (HEIs)

Comparative Analysis of Data Mining Classification Algorithm Performance for Searching Prospective Student Interests

Contact Info

Product

Resources

About