Special Issue - 2017 International Journal of Engineering Research & Technology (IJERT)

ISSN: 2278-0181
ICIATE - 2017 Conference Proceedings

Student Performance Analysis System using Data

Mining
Disha Kalambe Anita Labade
Department of Information Technology Department of Information Technology
Atharva College of Engineering Atharva College of Engineering
Mumbai, India Mumbai, India

Surabhi Khedekar Komal Mahajan

Department of Information Technology Assistant Professor
Atharva College of Engineering Department of Information Technology
Mumbai, India Atharva College of Engineering
Mumbai, India

Abstract—In this age of computerization, education the students excel and where not and what are their abilities
has also re-constructed itself and is not limited to old which can be enhanced. The analysis will summarize the
lecture method. Nowadays, lots of data is collected in outcome and will classify students based on the results. This
educational databases, but it remains unutilized. In order system will recognize interest of student in particular areas.
to get required benefits from such a big data, powerful The proposed system will also classify the students who are
tools are required. Data mining is an emerging powerful eligible for placements based on company’s criteria.
tool for analysis. The previous system doesn’t give the
guidance to student based on the overall performance. II. LITERATURE REVIEWED
The proposed system presents the analysis of student
performance on the basis of academic performance, Brijesh Kumar Baradwaj and Saurabh Pal have
extra-curricular activities, strengths, weakness and proposed a system that uses data mining methodologies to
hobbies. The proposed system uses classification study students‟ performance in the courses. Data mining
algorithm and guides them by displaying the areas where provides many tasks that could be used to study the student
they need to do improvement in order to contribute to a performance. In this research, the categorization task is
used to evaluate students’ performance and as there are
student's overall growth by generating a score card for
many approaches that are used for data classification, the
the same. The proposed system will give all the required
decision tree method is used here. Data like Attendance,
information of each and every student.
Assignment marks Class test, and Seminar were gathered
from the student’s management system, to predict the
Keywords—Data Mining, Classification, Academic performance at the end of the semester. This paper
Performance, Score card investigates the correctness of Decision tree techniques for
predicting student performance.
I. INTRODUCTION Koma lJirage, Rucha Choudhari, Varsha Gupta, Anil
The academic performance of student is usually stored in Patthe and Disha Maind have proposed a system that is
various formats like files, documents, records etc. The going to find out student trends on the basis of outcomes of
available data would be analyzed to extract useful tangible records as well as indirect surveys. This data
information. It becomes difficult to analyze student data by collected will be processed by k-means technique of data
applying statistical techniques or other traditional database mining. A result from k-means algorithm will be
management tools. Hence there is a need to develop an recognizing as Trend. This trend will help us to track where
automated tool for student performance analysis that would the students excel and where not and what are their abilities
analyze student performance and will guide them by which can be enhanced. The analysis will summarize the
displaying the areas where they need improvement, in order to result and will classify students based on the outcome. This
contribute to a student's overall growth by generating a score system will recognize interest of student in particular areas.
card for the same. The proposed system will display results of To empower our student for substantial contribution to
student performance on a single click action by the user, thus technological, economical, social and entrepreneur
inducing automation and reducing efforts of staff in analyzing progress of the society.
student performance manually. The proposed system finds out
Bo Guo, Rui Zhang ,GuangXu,ChuangmingShiand Li
student trends on the basis of outcomes of students’ academic
Yanghave proposed a system that present a deep learning
performance, strengths, weakness, hobbies and extra-
curricular activities. Academic data includes unit test, architecture for predicting students’ performance, which
student’s theory, practical’s and term work marks. This data takes advantages of unlabelled data by automatically learning
gathered will be processed by classification algorithm of data multiple levels of representation. This system pre-train
mining. A result from classification algorithm will be hidden layer of features layer wisely using sparse auto-
recognizing as Trend. This trend will help us to track where encoder, and then use supervised training for fine-tuning the

Volume 5, Issue 01 Published by, www.ijert.org 1

Special Issue - 2017 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
ICIATE - 2017 Conference Proceedings

parameters. This system train model on a relatively large real to know that the student is weak or strong and the student is
world students dataset, and the experimental results show the eligible for the placements.
effectiveness of the propose method.
IV. METHODOLOGY
III. PROPOSED SYSTEM
A. WEKA:
It contains a collection of visualization tools and algorithms
for data analysis and predictive modeling, together with
graphical user interfaces for easy access to these functions.
The system is not so much a single program as a collection of
inter-dependent programs bound together by a common user
interface. Typically these modules fall into three categories:
data set processing, machine learning schemes, and output
processing.

Fig. 2. Steps of extracting knowledge

Fig. 1. System Block Diagram

The proposed system extracts all the students’ data from the
A. Description of block Diagram: database. Then selects the desired data, split the dataset into
test and training sets and preprocess it as filter out features.
The proposed system include an user profile creator to Then the data is transformed into the data mining and the
provide user interface, user login, student performance evaluation is done.
analyzer, Extra-curricular activities, Academic performance,
score card generator, student performance credit card, student
B. ID3 Algorithm:
development card, achieved credit, passing criteria card and
semester-wise student performance attribute card. Students ID3 is a simple decision tree learning algorithm.
will be grouped into categories like distinction, first class,
The basic idea of ID3 algorithm is to build the
higher second class, second class and pass class based on
decision tree by employing a top-down, greedy search
passing criteria.
through the given sets to test each attribute at every
1) Admin Login: This module is used for loginfor the tree node. In order to pick the attribute that is most
admin user of the system, so that admin can manage useful for categorizing a given sets, we introduce a
staff, create and manipulate subjects and student, metric - information gain. [3]
assign subject to each semester and staff to each
subject. ID3 (Examples, Target_Attribute, Attributes)
2) Faculty Login: This module is used for loginto a 1) Create a root node for the tree
faculty so that they can access the system and can 2) If all examples are positive, Return the
add marks to each student for their respected single-node tree Root, with label = +.
subject. Also they can add strength and weakness of 3) If all examples are negative, Return the
a student which can be both used to perform an single-node tree Root, with label = -.
analysis of a student. 4) If number of predicting attributes is empty,
Student Login: This module is used for loginthe student who then Return the single node tree Root with
can then view their marks for each subject entered by the label = most common value of the target
staff. attribute in the examples.
5) Otherwise Begin
B. Flow of the purposed system: a ) A = The Attribute that best classifies
examples.
Step1: In the purposed system the user will first loginto the
system to initiate the process. b) Decision Tree attribute for Root = A.
c) For each possible value, vi, of A,
Step2: Then the user will get a form which containsfields like
Student Name, Student ID, Branch of the student, Academic d) Add a new tree branch below Root,
Year, Semester ETC. corresponding to the test A = vi.
Step3: Then from each of the field the user will get adata of e) Let Examples(vi) be the subset of examples that
an student individual or Semester wise or Branch wise or have the value vi for A
Year wise. f) If Examples(vi) is empty
Step4: Then it will also contain extra activitiesperformed by g) Then below this new branch add a leaf node
the students and from all that analysis the faculty will come with label = most common target values in the
examples

Volume 5, Issue 01 Published by, www.ijert.org 2

Special Issue - 2017 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
ICIATE - 2017 Conference Proceedings

h) Else below this new branch add the sub tree

ID3 (Examples(vi), Target_Attribute,
Attributes – {A})
6) End
7) Return Root.

V. CONCLUSION

The proposed system displays the results of student on a

single click action by the user, thus inducing automation and
reducing efforts of staff in analyzing student performance
manually. The data collected is processed by classification
algorithm of data mining. The proposed system helps to the
students and the teachers to improve the division of the
student. The proposed system also work to identify those
students who require special attention to lessen fail ratio and
taking proper action for the next semester examination. The
proposed system also classifies the students who are eligible
for placements based on company’s criteria.

REFERENCES

[1] Brijesh Kumar Baradwaj and Saurabh Pal “Mining Educational

Data to Analyze Students‟ Performance” (IJACSA) International
Journal of Advanced Computer Science and
Applications,Vol.2,No.6,2011.
[2] Komal Jirage1, RuchaChoudhari, Varsha Gupta, Anil Patthe4 and
DishaMaind “ Student Performance Analysis Based on Learning”
International journal for research in emerging science and
technology, volume-2, issue-3, march-2015.E-ISSN No: 2349-
7610
[3] Bo Guo, Rui Zhang, GuangXu, ChuangmingShiand Li
Yang“Predicting Students Performance in Educational Data
Mining”International Symposium on Educational Technology,
2015
[4] SnehalKekane, DipikaKhairnar, RohiniPatil, Prof. S.R. Vispute and
Prof. N. Gawande “International Journal of Innovative Research in
Computer and Communication Engineering” Vol. 4, Issue 1,
January 2016, ISSN(Online): 2320-9801,ISSN (Print): 2320-9798.
[5] PoojaThakar,Anil Mehta, Ph.DManisha, Ph.D“Performance
Analysis and Prediction in Educational Data Mining: A Research
Travelogue” International Journal of Computer Applications (0975
– 8887) Volume110–No.15,January2015.

Volume 5, Issue 01 Published by, www.ijert.org 3