A Unified Model of Clustering and Classification to Improve Students’ Employability Prediction

Abstract

Abstract-DataMining is gaining immense popularity in the field of education due to its predictive capabilities. But, most of the prior effort in this area is only directed towards prediction of performance in academic results only. Nowadays, education has become employment oriented. Very little attempt is made to predict students' employability.Precise prediction of students' performance in campus placements at an early stage can identify students, who are at the risk of unemployment and proactive actions can be taken to improve their performance.Existing researches on students' employability prediction are either based upon only one type of course or on single University/Institute; thus is not scalable from one context to another. With this necessity, the conception of a unified model of clustering and classification is proposed in this paper.With the notion of unification, data of professional courses namely Engineering and Masters in Computer Applications students are collected from various universities and institutions pan India. Data is large, multivariate, incomplete, heterogeneous and unbalanced in nature. To deal with such a data, a unified predictive model is built by integrating clustering and classification techniques. Two-Level clustering (k-means kernel) with chi-square analysis is applied at the pre-processing stage for the automated selection of relevant attributes and then ensemble vote classification technique with a combination of four classifiers namely k-star, random tree, simple cart and the random forest is applied to predict students' employability. Proposed framework provides a generalized solution for student employability prediction. Comparative results clearly depict model performance over various classification techniques. Also, when the proposed model is applied up to the level of the state, classification accuracy touches 96.78% and 0.937 kappa value.

Predicting Student Performance using Classification and Regression Trees Algorithm

“…The choice of the algorithm to be used depends on factors such as the performance that can be achieved in the specific application domain, the level of results accuracy or the comprehensibility of the model. Classification and clustering are perhaps the most frequently mining tasks for performing mining on large data sets [21].…”

Supervised Support Vector Machine in Predicting Foreign Exchange Trading

“…The mining data in Rumania stock using neural network models for price prediction also can be seen in [6]. The neural network such as MLP (multilayer perceptron) is not only successful in classifying of electroencephalogram (EEG) [12,21] but also it has been used to predict the future price of stock code in financial field. The results have shown the advantages of using supervised learning techniques in predicting classification problems.…”

Decision Support System to Determine Promotional Methods and Targets with K-Means Clustering

“…Pooja Thakar et al [7] create a model to predict students' abilities. Most failures of students in academic education caused there is no match between the ability of students and material provided or not placed on the appropriate campus.…”

“…A combination of methods is also often done to obtain optimal results. Such as clustering fusion with classification to know the student's ability in effort on the student placement at the campus which is based on the ability of each student [7]. Marketing party can utilize the pile of the data as a supporter in making a decision such as determining promotional methods and promotional targets.…”