Discovery some of the influencing patterns in the
academic performance of the students of the Faculty
of Education using the Association Rules technique.
Case study: Faculty of Education, Afif
1
*1 Noha Hassan Osman Rajab , 2 Dr Saif Eldin Fattoh
Lecture,Faculty of Education of Afif ,Shaqra University ,Kingdom of Saudi Arabia
2
Dean of Emirates University ,Khartoum,Sudan
Email:[email protected](*Corresponding Author)
Abstract
This research aims to discover some of the dominant patterns in the academic data stored in the database Shaqra University of the
Faculty of Education in Afif that influential in the academic performance of the students of the Faculty of Education of AFiF for
the year 1438 and the research study applied in the field discovery of knowledge (data mining) by choosing Association
Rules technique, which is an Apriori algorithm and this algorithm has helped to find patterns that can significant indicators are
given between the percentage of students at the secondary level, the degree of capacity, the choice of specialization and the
cumulative rate in two semesters The college graduates from the student statements accepted in the first semester of the academic
year 1437/1438. This study is trying to read, interpret and display results, and the technology of the Association Rules has been
chosen to fit this research and is one of the methods of data mining that helps decision makers make the right decisions.
Key words: Data mining , Knowledge discovery in databases (KDD),Association Rule Techniques ,Apriorii Algorithms
1- Introduction:
University education institutions play an active role in the
development of human cadres, and university education is the
most important and reliable component of the human race,
which is the central focus of development. Academic
performance is considered to be among them and there are
many variables that influence academic performance of
university students, as universities are entirely dependent on
students and are the most important group in an educational
institution.
1.1 Data Mining
Data mining discovers patterns and relationships hidden in
data, and is actually part of a larger process called “knowledge
discovery” which describes the steps that must be taken to
ensure meaningful results. Data mining software does not,
however, eliminate the need to know the business, understand
the data, or be aware of general statistical methods. Data
mining does not find patterns and knowledge that can be
trusted automatically without verification. Data mining helps
business analysts to generate hypotheses, but it does not
validate the hypotheses.[5].
1.2-Knowledge discovery in databases (KDD)
Knowledge discovery in databases (KDD) is the process of
discovering useful knowledge from a collection of data. This
widely used data mining technique is a process that includes
data preparation and selection, data cleansing, incorporating
prior knowledge on data sets and interpreting accurate
solutions from the observed results.[3] .
1.3- Association Rules
Association rules are if/then statements that help uncover
relationships between seemingly unrelated data in a relational
database or other information repository.[2].
An association rule has two parts, an antecedent (if) and a
consequent (then). An antecedent is an item found in the data.
A consequent is an item that is found in combination with the
antecedent.
Association rules are created by analyzing data for frequent
if/then patterns and using the criteria support and confidence to
identify the most important relationships. Support is an
indication of how frequently the items appear in the
database. Confidence indicates the number of times the if/then
statements have been found to be true. [2]
Association Rules find all sets of items (item sets) that
have support greater than the minimum support and then using
the large item sets to generate the desired rules that
have confidence greater than the minimum confidence.
The lift of a rule is the ratio of the observed support to that
expected if X and Y were independent
1.4-
Apriori algorithm
Apriori algorithm is an algorithm for frequent item set
mining and association rule learning over transaction
databases. Its followed by identifying the frequent individual
items in the database and extending them to larger and larger
item sets as long as those item sets appear sufficiently often in
the database. The frequent item sets determined by Apriori can
be used to determine association rules which highlight general
trends in the database. [4].
Apriori Algorithm: Pseudo code
Join step: is generated by joining with itself
Prune Step: any (k-1) item set that is not frequent cannot be a
subset of a frequent k-item set
Pseudo-code:
2- Search problem
The Faculty of Education of Afif has a very rich database of
academic data for students, pupils, programs, results,
educational outcomes, etc. since the establishment of the
university 1431 to date. This vast amount of data,
although well known, has not yet been effectively exploited in
the knowledge of success factors and failures, and the
prevailing patterns have not been known affecting the
academic performance of the student, who is one of the most
important elements of university education and of the reasons
for the dropout or diversion as well as the reasons for the
student's failure or superiority and what the patterns are. This
data-rich database can be used to support university decision
makers and colleges, and the use of techniques such as
Association Rules can provide results show relationships
between different pattern within the university structure to
help identify points of weakness and strength to do what is
useful in evaluating performance within the university.
3- Search Objectives
This study provides an application in the field of knowledge
discovery to learn about the dominant patterns in the academic
data of female students that contribute to the development of
the university's educational process through the application of
the rules of engagement technology to:
 To make use of the academic data of the university
and of the college to discover the dominant and
influential patterns of academic performance.
 2. Discovering patterns helps to improve and develop
the educational process in the college.
 3. Discovering the dominant patterns helps to identify
the causes of the failure or superiority of female
students and thus helps the college management to
learn about and address development constraints.
 4. Produce results that help decision-making to
develop the college's education and learning
outcomes.
4-
Research methodology:
In this study the analytical descriptive approach has been used
where a method has been developed to discover influencing
patterns in student academic performance based on the
methods currently used to discover knowledge (data mining
systems). This method aims to discover the relationships
between data the academy for female students are relevant to
the academic performance of the student. This reduces the
problems resulting from the poor methods used in the
development and ordering of courses and the application of the
Rules of Association (Association Rules) technique has been
applied to the student data.
5- Study Limits:
Objective:
Application of the Association rules technique to the academic
data of the first level students at the Faculty of Education of
AFEF.
Spatial:
Faculty of Education of the Shaqra University in the Kingdom
of Saudi Arabia.
Temporal: First semester... For the year... 1437
6- Theoretical framework:
Shaqra University database contains the data of female
students and students at various faculties, disciplines and
faculty of Education with one of its faculties, including many
sections include English, mathematics, Physics, Chemistry,
Biology and Home economics, and contain academic student
data.
7- Previous studies:
In the first study [1], the researcher reviewed the applications
of data mining in higher education, and the research presented
a theoretical study on the data of the students of the University
of IUS so that the Association Rules Technique (association
Rules) The fact that the study was theoretical was the focus of
the research on explaining data mining techniques and
algorithms and their importance in supporting decision-making
in higher education institutions.
9- Analysis and interpretation of results
The second study [6] has taken care of the applications of
prospecting in educational data and is based on the inputs and
 After compiling and processing data, the Apriori
outputs of the educational process and how they affect each
algorithm has been applied to the data and we get the
other and the neural networks method has been used to learn
following table
about the relationships between the curriculum and the
approved hours of students as well as other useful conclusions
Table No(2)
for decision makers at universities.
Numbers of Rules
Previous studies talk about data mining and explain it in detail
Confid Supp
and do not care about discovering influencing patterns but
Consequen
NO
Antecedent
ence(
ort
Lift
most studies take the direction more theoretical than applied in
t
%)
(%)
this study, we try to know what relationships exist within the
2.000 ≤ CGPA <
databases that affect the academic performance of female
Secondary
3.000
students.
1
Department=economi
c
8- Methodology
The study community
The students of the Faculty of Education in AFEF is a shaqra 2
university
 Sample study:
First-level students for the university year 1437/1438
 Implementation of the study:
3
.Obtain data from the database and save it in an external file.
The data used in this study is data stored within the database of
the Shaqra University. The data included students accepted for
the first semester of the year 1437/1438
4
That was obtained in the form of files, PDF, and Excel.

Nationalit
y
Departme
nt
Birthday
Input
year
Civil
number
integ
er
integ
er
integ
er
integ
er
integ
er
Field
name
Secondary
ratio
Degree of
achieveme
nt
Degree of
capacity
Weighted
degree
CGPA
input date
Select
Data
type
integ
er
integ
er
integ
er
integ
er
integ
er
integ
er
integ
er
≤
100
7.89
3.11
64≤
Degree
of
capacity< 72
3.000<CGPA<4.9
department
= english
100.33
6.14
2.15
department = math
CGPA > 4.000
72
≤
Degree of
capacity<
81
93.7
6.14
3.17
department = math
64
≤
Degree
capabilities
< 72
89.33
7.02
2.9
93.890 ≤
Secondary
ratio
<
96.850
100
7.89
2.04
96.91
7.89
3.11
5
72 ≤ Degree
capacity< 81
CGPA > 4.000
6
Secondary ratio ≤
87.970
department =biology
2.000
CGPA
3.000
64 ≤ Degree
capacity< 72
CGPA > 4.000
of
department
= math
728.89
6.14
2.96
64 ≤ Degree
capacity < 72
CGPA>3.5
of
8
department
= physics
100.1
7.02
2.9
9
93.890 ≤ Secondary
ratio < 96.850
CGPA > 4.000
72
≤Degree of
capacity <
81
90.2
7.89
2.04
10
department
chemistry
CGPA>4.00
72
≤Degree of
capacity <
81
98.58
6.14
2.15
Data processing and disposal of fields that do not
affect the discovery of patterns such as student name,
7
university number, year of admission, civil registry
Table No(1)
Filed
Data
name
type
Student
Integ
ID
er
Student
integ
name
er
ratio
87.970
of
=
≤
<
Association Rule With Confidence
The table No(2) contains a set of rules that help to
know the strength and weakness of the academic performance
of first-level students, including:
 The secondary rate is a very influential pattern of the
cumulative student's rate of two classrooms.
 The degree of capacity testing in addition to
specialization is linked to the cumulative student rate.
From the table above we can conclude that the disciplines
"biology" and "mathematics" are advanced in terms of
academic performance on the rest of the disciplines
The number of records in the data and trust level has been set
to 0.75 and 1. And when she was trusting in the number of 0.75
rules that increased
It is set out in the table above. From the data set it is clear that
the Faculty of education of AFEF has patterns and rules
associated with its academic data,
It can be said that the specific patterns
IF 93.890 ≤Secondary ratio< 96.850 or
capacity < 81
Then CGPA > 4,000
IfElse 2.000 ≤ CGPA < 3.000
72 ≤Degree of
In this search one of the technologies of the Association Rules ,
the Apriori algorithm is applied to the Faculty of Education of
the chaste, which follows the University of Blonde to discover
the patterns influence academic performance and assist
departments in improving and developing education and
learning outcomes, and data included academic data for
students accepted in the first semester of the academic year
1437/1438 and the cumulative female students in two
classrooms (first and second) and findings that help to improve
the academic performance of female students and meaningful
relationships between the cumulative student rate and the
percentage obtained by the student of secondary, degree of
testing and selection of specialization. In addition to the
relationships between the cumulative rate of female students
and some subjects that help to predict the dropout of female
students from the university, we have not touched on it in this
research, which makes it imperative for the university's
admissions and registration department to look at the results to
take advantage of them in raising the level of future students
and learners.
11- References:
Figure 1: showing the rules of association
between the academic data of female
students
Figur 2: shows the rules of correlation
between academic data for female students
10- Conclusions
[1]. Abdullah Hussein Al-Hashiedy, "Data Mining Applications
in Higher Education", Master
thesis in Computer Information Systems, Arab Academy of
Financial and Banking
Sciences..
[2]. Bhardwaj, A., Sharma, A., & Shrivastava, V. (2012). Data
mining techniques and their implementation in blood bank
sector–a review. International Journal of Engineering Research
and Applications (IJERA), 2(4), 1303-1309.
[3].Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996).
From data mining to knowledge discovery in databases. AI
magazine, 17(3), 37.
[4].Han, J., Pei, J., Yin, Y., & Mao, R. (2004). Mining frequent
patterns without candidate generation: A frequent-pattern tree
approach. Data mining and knowledge discovery, 8(1), 53-87.
[5].Rygielski, C., Wang, J.-C., & Yen, D. C. (2002). Data
mining techniques for customer relationship management.
Technology in society, 24(4), 483-502.
[6]. Jing Luan, “Data Mining Applications in Higher
Education”, 2004.