Student’s Performance Prediction using Deep Learning and Data Mining Methods
Jabeen Sultana1, M. Usha Rani2, M.A.H. Farquad3

1Jabeen Sultana, Research Scholar, Department of Computer Science, SPMVV University Tirupati (Andhra Pradesh), India.
2M. Usha Rani, Department of Computer Science, SPMVV University, Tirupati (Andhra Pradesh), India.
3M.A.H. Farquad, Department of Computer and Information Systems, Islamic University of Madinah, Madinah Al-Munawwara, Kingdom of Saudi Arabia.
Manuscript received on 07 June 2019 | Revised Manuscript received on 30 June 2019 | Manuscript Published on 04 July 2019 | PP: 1018-1021 | Volume-8 Issue-1S4 June 2019 | Retrieval Number: A11880681S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Educational organizations are unique and play utmost significant role for the development of any country.As Education transforms the lives of individuals, families, communities, societies, countries and ultimately the world! This is why we live comfortable lives today. Now a day’s education is not limited to only the classroom teaching but it goes beyond that like Online Education System, Web-based Education System, Seminars, Workshops, MOOC course. becomes It’s more challenging to Predict student’s performance because of the huge bulks of data stored in the environments of Educational databases, Learning Management databases.Students’ performance can be evaluated with the help of various available techniques.Data Mining is the most prevalent techniques to evaluate students’ performance and is extensively used in Educational sector known as Educational data mining. It is evolving area of study that emphases on various techniques of data mining like classification, prediction, feature selection. It is employed on learning recordsor data related to education to predict the students’ performance and learning behavior by extracting the hidden knowledge. EDM is a methodology or like a procedure which is used to mine valuable information and patterns or forms from a massive educational database. Subsequently, the student’s performance is predicted from the obtained useful information and patterns. The prime motto of our study is to discover the performance of students using some classification techniques and discovering the best one which yields optimal results. Educational Dataset is collected from a Saudi University database. The dataset is pre-processed to filter duplicate records; missing fields are identified and filled with the destined data. Deep Learning techniques like Deep Neural Net and Data Mining techniques like Random Forest, SVM, Decision Tree and Naïve Bayes are employed on the data set using Weka and Rapid Miner tools. Results achieved are evaluated on few metrics. Deep Neural Network and Decision Tree outstands in predicting students’ performance compared to other techniques by producing deep predictions and obtains the best results like high accuracy, kappa-statistic, Sensitivity and Specificity are also determined.
Keywords: Educational Data Mining (EDM), Deep Learning, Random Forest, Decision Tree, Naïve Bayes and SVM.
Scope of the Article: Deep Learning