Data Mining Model for Effective Data Analysis of Higher Education Students Using MapReduce

Abstract

Abstractata analysis plays an important role for decision support irrespective of type of industry like any manufacturing unit and educations system. There are many domains in which data mining techniques plays an important role. Educational data mining concerns with developing methods for discovering knowledge from data that come from educational domain. In this paper we used educational data mining to improve graduate students' performance, and overcome the problem of strong and weak of graduate students. In our case study we try to extract useful knowledge from graduate students data collected from the BV's College of Engineering . The data include four years of period [2012][2013][2014][2015][2016]. After preprocessing the data, we applied data mining techniques to discover classification, clustering and outlier detection rules. In each of these tasks, we present the extracted knowledge and describe its importance in educational domain. Data mining techniques are analysis tools that can be used to extract meaningful knowledge from large data sets. This paper is designed to present and justify the capabilities of data mining in the context of higher educational system. Keywords-Map-Reduce, Classification, Performanace, Data Mining, Analysis. I. INTRODUCTIONNow a day"s large quantities of data is being accumulated. Data mining is the process of discovering interesting knowledge from large amount of data stored in database or other information responsibility. The educational system in India is currently facing several issues such as identifying students need, personalization of training and predicting quality of student interactions. Educational data mining (EDM) provides a set of techniques which can help educational system to overcome this issue in order to improve Learning experience of students as well as increase their profits. Manual data analysis has been around for sometimes now, but it creates bottleneck for large data analysis. The transition won"t occur automatically; in this case, we need the data mining. Data mining software allow user to analyzed data from different dimensions categorized it and summarized the relationship, identified during mining process .The topic of explanation and Data analysis of academic performance is widely researched. Data Mining Techniques is the promising methodology to extract valuable information in this objective. The data collected from different applications require proper method of extracting knowledge from large repositories for better decision making. Knowledge discovery in databases (KDD), often called data mining, aims at the discovery of useful information from large collections of data. In this perspective, Data Mining can analyze relevant information results and produce different perspectives to understand more about the students" Performanace so as to customize the course for student learning.The main objective of higher education institutes is to provide quality education to its students and to improve the quality of managerial decisions. In this perspec...

Learning Analytics to identify dropout factors of Computer Science studies through Bayesian networks

“…Diverse types of algorithms and techniques can be used for information retrieval from educational databases (Romero & Ventura 2010). In this regard, several works have tried to predict the academic performance and the risk that students drop out (Aulck et al 2016), (Barbosa, Serra & Zimbrão 2015), applying different methods such as classification (Kostopoulos, Kotsiantis & Pintelas 2015;Patil et al 2017), regression (Bowers 2010;Burgos et al 2017;Oyerinde 2017), decision trees (Quadri & Kalyankar 2010;Sivakumar, Venkataraman & Selvaraj 2016;Pereira, Pai & Fernandes 2017;Kabra & Bichkar 2011;Asif, et al 2017), genetic algorithms (Marquez-Vera et al 2013), association algorithms of data mining, or a combination of several methods (Yukselturk, Ozekes & Türel 2014;Costa et al 2017;Lykourentzou et al 2009) for their prediction in educational setting. To make such prediction, several attributes are used such as academic, social, demographic, personal and family data.…”

Predictive Modelling of Student Dropout Using Ensemble Classifier Method in Higher Education

“…Naïve Bayes as a simple probabilistic classifier can be developed easily on a large amount of data because it does not need complex parameter estimation which makes it outperform over another sophisticated method [2]. Naïve Bayes was also able to learn conditional probability feature separately so it also has been very effective in classifying small datasets.…”

“…Drop out is not a novelty thing but still being a serious topic which attracts researchers' attention due to its impact on decreasing higher education values and can be an adverse impact on the social environment, where other prospective students lose their opportunity to study in higher education. In the last 10 years, many research has been carried out by utilizing technology to find ways how to prevent dropout issues, which is called Education Data Mining [2]. Educational Data Mining (EDM) represents a variety of algorithmic methods to address various problems in the educational system and even generates new knowledge, to calculate student's academic performance, predict student's behavioral and especially to predict variables or indicators that influence dropout in higher education [3].…”

Novel Approach with Deep Learning Models For Melanoma Skin Cancer Detection

“…The SVM algorithm's accuracy was about 78 %. Shankar M. Patil and Dr. Praveen Kumar [8]The first and most significant step is data collection and analysis because it is essential for decision support in all industries.…”