A comparison between deep learning, naïve bayes and random forest for the application of data mining on the admission of new students

Abstract

<span id="docs-internal-guid-5a78994c-7fff-41c1-c57f-91661e44674c"><span>The process of admitting new students at Universitas Islam Negeri Raden Fatah each year produces a lot of new student data. So that there is an accumulation of student data continuously. The purpose of this study is to compare deep learning, naïve bayes, and random forest on the admission of new students as well as being one of the bases for making decisions to determine the promotion strategy of each study program. The data mining method used is knowledge discovery in database (KDD). The tools used are rapid miner. The attributes used are student ID number, name, program study, faculty, gender, place of birth, date of birth, year of entry, school origin, national examination, type of payment, and nominal payment. The new student data used from 2016 to 2019 was an 18.930 item. The results of this study used deep learning bayes results resulted in an accuracy value of 52.65%, naïve bayes results resulted in an accuracy value of 99.79%, and random forest results resulted in an accuracy value of 44.65%.</span></span>

Automatic COVID-19 prediction using explainable machine learning techniques

“…Random forest: The random forest model combines and uses various classifiers to explain regression and classification problems ( Nurhachita and Negara, 2021 ). It utilizes ensemble machine learning techniques.…”

Masters and Doctor of Philosophy admission prediction of Bangladeshi students into different classes of universities

“…RF model is an approach based on the ensemble method. It is one of the popular approaches which offers an optimized predictive algorithm by combining several models [9]. Several weak learners are combined to build a more robust model in the ensemble method [21], [22].…”

“…According to this year's Quacquarelli Symonds (QS) world university rankings [8], we have divided the accepted universities into four classes. Subsequently, we have developed three different approaches (each for the MS and PhD students' data) to make the model based on DT [5] and RF [9] approaches for assessing the possibility of a student's admission to a particular class of university. Finally, we have reported all the ML algorithms' performance for both the MS and PhD applicants' data in terms of the evaluation metrics, e.g., precision, recall, F1-score, accuracy, and confusion matrix [10].…”

Knowledge discovery in manufacturing datasets using data mining techniques to improve business performance

“…Industry 4.0 has grown and generated enormous attention in data analytics and automation in the manufacturing technology field [4]. Information technology has a great contribution in many organizations that collect, manipulate, and analyze data in their huge databases [5]. Previously, when the business was entirely based on manual procedures, it was common to analyze and keep updates of the business status, but the main problem was that even after a lot of hard work, it was very difficult to apply analytics processes and make any useful decision regarding future business [6].…”