TABLE OF CONTENT

Table of Content
List of Figures
Introduction
About the data
User Requirements
The Objectives
Features Available
System Requirement
Analysis
 LIST OF FIGURES

Figure 1 : Flow of the project.

Table 1: List of original attributes
Table 1: List of deducted attributes

Table 6.0: List of software requirement.

 INTRODUCTION

Nowadays, Mathematics is an important subject for today’s generations. It has been included in
many aspects such as natural science, engineering, medicine, finance and social sciences. Hence,
to be dominant, someone need to improve their mathematics in life to make things easier and
controllable.
In school today, mathematics has become a core subject for students to be learned and the
syllabus has been upgraded days by days. Hence, it has bring a huge impact towards student’s
way of learning. The reason is the old syllabus is book-based oriented way of learning. However,
Ministry of education has upgraded the syllabus, so that the students will implementing the
concepts of critical and analytical thinking in solving mathematical problems.
As the consequences of Ministry enforcement, it has affected student’s grade in
mathematics because the students need to be more creative in solving problems in examination.
This will bring more bad than good to the students because students have different level of
thinking. As a result, students’ grade in mathematics will drop gradually.
Therefore, actions need to be taken to prevent this problem getting bigger. There are
several actions or initiative that need to be taken by all parties:
1. Student :
- Students must be able to manage their study and personal time wisely.
- Students should get family support in term of moral and finance to make sure that
they can pursue their study excellently.
- Students need to make their own timetable to make sure their activities are well
organized.
- Students should
2. School :
- School authorities should organized an intensive mathematical program for the
students.
- School may provide financial aid for students who cannot afford their study and
tuition fees.
1. METHODOLOGY

DATA COLLECTION

DATA PREPROCESSING

DATA ANALYSIS

DATA VISUALIZATION

DATA INTREPRETATION

Figure 1 : Flow of the project.

i ) DATA COLLECTION :

The dataset of Math Students has been collected from Kaggle.com website. Originally,
this dataset is from UCI dataset repository. This dataset contains the final scores of
students at the end of a math programs with several features that might or might not
impact the future outcomes of these students. Table 1 below, shows the list of attributes
that originally comes from Kaggle dataset:

School Father’s job Activities Weekend alcohol

Sex Reason Nursery Health status
Age Guardian Higher education Absences
Address Travel time Internet First grade
Family size Study time Romantic relationship Second grade
Parent status Failures Family relationship Final grade
Mother’s education School support Free time
Father’s education Family support Go out
Mother’s job Extra paid class Work day alcohol

Table 1: List of original attributes

ii ) DATA PREPROCESSING :
At this stage, since this data does not contain any outlier and extreme value, thus the
cleaning process is not necessary. Next step, the number of attributes have been deducted
from 33 to 17 attributes. This is because, those data are not necessary to be used in this
project. The only attribute that left are:

School Student school

Sex Student’s Gender
Address Student’s home address type
Family Size Number of family members
LE3 – less than or equal to 3
GT3 – greater than 3
Parent Status Parent’s cohabitation status
T – living together
A – living apart
Father’s Job Father’s Job
Reason Choosing Reason to choose this school
Study Time Weekly study time
Failures Number of past class failures
Family Support Family educational support
Activities Extra-curricular activities
Romantic Relationship In a romantic relationship or not
Family Relationship Quality of family relationship
Absences Number of school absences
First grade First Period Grade ( 0 – 20 )
Second grade Second Period Grade ( 0 – 20 )
Final grade Third Period Grade ( 0 - 20 )

Table 1: List of deducted attributes

iii ) DATA ANALYSIS :

 The data that was collected from Kaggle has been analyzed associated with user
requirement. In the next section of this project (6- Analysis) will be explain more clearly
about data analysis.

iv ) DATA VISUALIZATION :
In this stage, the dashboard has been developed as a process of fulfilling user requirement
in visualizing the data. There are several graph that can be created to show the data in
graphical form.

v ) DATA INTERPRETATION :
From the chartered graph, the interpretation will be made to help user in making decision
for business purpose. At this process, the interpretation plays a huge role to make the user
making the right decision for the upcoming future. Hence, it becomes admin
responsibilities to interpret the data precise and accurately without any doubt.

2. THE OBJECTIVES
There are a few objectives in this project:
1. To plot the graph or the customer’s data.
2. To design desktop to allow data exploration for future action to make decision.
3. To analyze the customer’s insight data by referring to the plotted graph.

3. USER REQUIREMENT

This visualization project helps to uncover the differences by comparing the student’s
improvement in Mathematics score between rural and urban student. It is very helpful for the
user to visualize the data by analyzing the effectiveness of family relationship towards the
failure. This visualization help to view and predict what kind of family relationship will affect
the student score. Furthermore, the relationship between study time and activities also affect the
student’s past failure which can be analyze from the graph in more detail. Lastly, from this
visualization project, we can justify either the financial support provided by the family depends
on the father’s type of occupation or not

 The comparison of student’s improvement in Mathematics Score between

rural & urban.
 The effectiveness of family relationship towards students failure.
 The relationship between study time and activities towards student’s past
failure.
 The financial support provided by the family depends on the father’s
occupation.
4. ANALYSIS
Analysis:
The stacked bar chart above illustrates the relationship between father’s job and family financial
support for student’s education. There are 5 types of father’s jobs which are health sector,
working at home, teacher, service sector and others. Besides, there are some family that provide
financial support for their children’s education and some are not.

For father’s job that comes from OTHERS such as business related jobs, manufacturing sectors
and etc. The total number of students that receive financial support from their family is 131
while the total number of students that do not receive any is 86. The reason why there are highest
number of students that received is because their father might have many income sources and
other asset properties to support their children. However, a large number of dependences in a
household might be a factors for the parents that could not afford their children education.

For fathers that worked in health sectors, there are 15 out of 18 students that have been
sponsored by their family but only 3 students do not receive financial support from their family.
Generally, from the graph most fathers give financial support to their children.
The pie chart above represents the relationship between number of failures and study time
according to their gender. There are four range of study time which are less than 2 hours, 2 – 5
hours, 5 – 10 hours and above 10 hours. From this graph, the results can be analyze by
identifying how the study time affected failures of the student. The total number of students who
never failed in mathematics exam are 312. For students that spent their study time between 2 to 5
hours a day, there are 158 students who was never failed in their exam compared to students who
spent their study time above 10 hours a day, there is only 26 students. Next, students who failed
three times in their mathematics exam consists of 9 and 7 students who study less than 2 hours
and between 2 to 5 hours respectively. The number of hours they spent for their study time
usually will affect the number of failures for them.
Usually, people thought that the more someone spent time for their study, the less number of
failures will be. From this graph, the assumption becomes wrong as the perfect number of hours
for study time is between 2 to 5 hours which is the most number of students never failed their
examinations. Students who studied above than 10 hours can result in underperforming exams.
This is because the students will be tired and their ability to learn become decreasing. Thus, this
will result less number of students that will never failed in their mathematics examination.

Generally, the probability of failures for students who spent their study time between 2 to 5
hours per day will be lowered. The reason is this range of time is suitable

U: Urban
R: Rural
F: Female
M: Male
GT3: Greater than 3

LE3: Less than 3

 5. FEATURES AVAILABLE

There are two parties in this system which are the user and Power BI. The user is the one who
will use the system for visualization purpose as a step to a good decision making.

The function of the desktop in Power BI is used to select, visualize and analyze the output of
data in a meaningful way. In the first function which is select the related attributes, users can
choose the attributes that they want to see the distribution among them. Then, the users will be
able to display the visual form of the selected attributes in the created dashboard.

Next, the users can change the background color as well as the color of the graph. Besides, they
also can choose to use the additional features to make the graph more interesting and more
attractive for the business purpose. As example, the user can choose to blur out the graph that
does not important and they can touch the graph to know the exact value of the data.

Then, the user can choose the graph that are available to view. The user can analyze and interpret
the output of the relationship between the selected attributes. Lastly, the user can choose either
want to continue with another type of relationship or to exit from the system. If the user choose
to continue, new attributes need to be selected in order to generate new kind of relationship.
However, if user click the exit button then the system will be closed.
6. SYSTEM REQUIREMENT

 Functional Requirement

1. The system can display the comparison between rural and urban student from
their improvement in Mathematics score.
2. The system can identify the effectiveness of family relationship towards student
failure.
3. The system can visualize the relationship between study time and activities
towards the student’s past failure.
4. The system can display whether the financial support provided by the family
depends on father’s occupation.

 Non-Functional Requirement

1. Availability
 Available to all the users to visualize the data.
 The system is open 24 hours a day and 7 days a week.

2. Serviceability
 Every month, the system will be serviced at the end of month (30th & 31th )
by 12 am until 6 am.

3. Usability
 The user must be able to access the system with or without prior
knowledge about the system.
 Since all the users are familiar with the general usage of application, no
special training is required. The system is user friendly which makes
easier

4. Regulatory
 After entered the system, there will be welcoming instruction provided to
guide the user into the system.

5. Manageability
 The user can manage to visualize the data with their own desire.
 However, certain type of data can only be visualize with suitable type of
graph.
Eg: Bar Chart can only visualized categorical type of data.
 Software Requirement

The project implementation will be done by using some software. The software is the
most important thing when developing a project, hence Table 6.0 shows the list of all the
software required in project implementation.

No. Software Description

1. Power BI Develop desktop for data visualization
2. Microsoft Office Word For documentation writing
3. Microsoft Office Power Point For presentation slide preparation
4. Microsoft Excel For data pre-processing
5. Google Chrome For data finding
6. Opera Mini For data finding

Table 6.0: List of software requirement.