ABSTRACT

The development of educational means has become a priority for most member states
and the rate regarding higher education presents a tendency to increase globally. This system can
predict the stream of the student by considering the parameters like favorite score, area of
interest, percentage obtained in SSC exam, average marks scored in Maths and Science subject
and the score of aptitude test. The system's main objective is to offer a quick and easy way to
appear the exam and it also provides results immediately after the exam. Multiple choice
examination is conducted to provide a special advantage to the students that can’t be found
anywhere else. This software application is built to check objective answers in an online
examination and allocate them to the user after verifying the answer. It can predict the streams
like Science, Commerce and Arts based on the various parameters mentioned above.
 CONTENT

S.NO. DESCRIPTION
INTRODUCTION
1.1 ORGANIZATION PROFILE
1 1.2 SYSTEM SPECIFICATION
1.2.1 HARDWARE REQUIREMENTS
1.2.2 SOFTWARE REQUIREMENTS
SYSTEM STUDY
2.1 EXISTING SYSTEM
2 2.1.1 DRAWBACKS
2.2 PROPOSED SYSTEM
2.2.1 FEATURES

SYSTEM DESIGN AND DEVELOPMENT

3.1 FILE DESIGN
3.2 INPUT DESIGN
3.3 CODE DESIGN
3 3.4 OUTPUT DESIGN
3.5 DATABASE DESIGN
3.6 SYSTEM DEVELOPMENT
3.6.1 MODULES
3.6.2 MODULES DESCRIPTION
4 TESTING AND IMPLEMENTATION
5 FEASIBILITY STUDY
APPENDIX
A. SYSTEM ARCHITECTURE
6
B. SAMPLE SOURCE CODE
C. SCREEN SHOT
CONCLUSION
7
BIBLIOGRAPHY
 1.INTRODUCTION

1.1 ORGANIZATION PROFILE

Higher education access prediction is an area in which the stream for SSC pass-out
students is predicted using some machine learning algorithms. The work done in this area
includes the attributes that affect the growth of the students and data mining approaches that
predict the outcomes. There is no full-proof system that can consider the various parameters like
favorite score, area of interest, percentage obtained in SSC exam, average marks scored in Maths
and Science subject and the score of aptitude test. We aim to build a system that can consider
these parameters and can predict the results mode effectively.

Many research papers consider on the data mining approaches to predict the outcome.
We are using a machine learning approach to predict the outcome. The algorithm we are using is
well suited for this kind of prediction system.
Today, increasing importance is given to predicting student performance due to the great
importance of this issue in the development of countries around the world because it depends
entirely on the educational process that leads to the production of a generation capable of taking
the responsibility of leading this country and its march towards development in all aspects of life
(scientific, economic, social and military, etc.). Also, the evaluation of students’ performance is
a reflection of the efficiency of educational institutions which is responsible for developing
successive generations in line with the different stages of the lives of people in every country.
+erefore, focusing on the development of the educational process is one of the utmost necessities
that push governments represented by educational institutions to make tremendous and
painstaking efforts to push the educational process towards continuous and escalating
development. Future knowledge can be obtained through prediction. +e higher the amount of
data is, as in large databases, the better the prediction is produced; this process is known as data
mining which is used to identify hidden information by exploring different data sources related
to different fields such as commercial, social, medical, and educational . +e knowledge presented
by different resources of educational data can be analyzed to extract desired information.
1.2 SYSTEM SPECIFICATION

1.2.1 HARDWARE REQUIREMENTS

• Processor - Intel Core i3

• Speed - 2.3 GHz

• RAM - 4 GB
• Hard Disk - 500 GB
• Key Board - Standard Windows Keyboard
• Mouse - Three Button Mouse
• Monitor - 17” LED

1.2.2 SOFTWARE REQUIREMENTS

• Operating System - Windows 10

• Language - Python

• GUI Tool - Anaconda

SOFTWARE ENVIRONMENT

1 FRONT END - PYTHON

Python is a high-level scripting language which can be used for a wide variety of text
processing, system administration and internet-related tasks. Unlike many similar languages, it’s
core language is very small and easy to master, while allowing the addition of modules to
perform a virtually limitless variety of tasks. Python is a true object-oriented language, and is
available on a wide variety of platforms. There’s even a python interpreter written entirely in
Java, further enhancing python’s position as an excellent solution for internet-based problems.
 Python was developed in the early 1990’s by Guido van Rossum, then at CWI in
Amsterdam, and currently at CNRI in Virginia. In some ways, python grew out of a project to
design a computer language which would be easy for beginners to learn, yet would be powerful
enough for even advanced users. This heritage is reflected in python’s small, clean syntax and
the thoroughness of the implementation of ideas like object-oriented programming, without
eliminating the ability to program in a more traditional style. So python is an excellent choice as
a first programming language without sacrificing the power and advanced capabilities that users
will eventually need. Although pictures of snakes often appear on python books and websites,
the name is derived from Guido van Rossum’s favorite TV show, “Monty Python’s Flying
Circus”.

The very Basics of Python

There are a few features of python which are different than other programming
languages, and which should be mentioned early on so that subsequent examples don’t seem
confusing. Further information on all of these features will be provided later, when the topics are
covered in depth. Python statements do not need to end with a special character – the python
interpreter knows that you are done with an individual statement by the presence of a newline,
which will be generated when you press the “Return” key of your keyboard. If a statement spans
more than one line, the safest course of action is to use a backslash (\) at the end of the line .

Invoking Python

There are three ways to invoke python, each with its’ own uses. The first way is to type
“python” at the shell command prompt. This brings up the

python interpreter with a message similar to this one:

Python 2.2.1 (#2, Aug 27 2002, 09:01:47) [GCC 2.95.4 20011002 (Debian prerelease)] on
linux2 Type "help", "copyright", "credits" or "license" for more information.

The three greater-than signs (>>>) represent python’s prompt; you type your commands
after the prompt, and hit return for python to execute them.

>>> print ’hello,world’

hello,world

The print statement automatically adds a newline at the end of the printed string. This is true
regardless of how python is invoked. (You can suppress the newline by following the string to
be printed with a comma.) When using the python interpreter this way, it executes statements
immediately, and, unless the value of an expression is assigned to a variable (See Section 6.1),
python will display the value of that expression as soon as it’s typed. This makes python a very
handy calculator:

>>> cost = 27.00

>>> taxrate = .075

>>> cost * taxrate

2.025

>>> 16 + 25 + 92 * 3

317

When you use python interactively and wish to use a loop, you must, as always, indent
the body of the loop consistently when you type your statements. Python can’t execute your
statements until the completion of the loop, and as a reminder, it changes its prompt from
greater-than signs to periods.

BASIC PRINCIPLES OF PYTHON

Python has many features that usually are found only in languages which are much more
complex to learn and use. These features were designed into python from its very first
beginnings, rather than being accumulated into an end result, as is the case with many other
scripting languages.

Basic Core Language

Python is designed so that there really isn’t that much to learn in the basic language. For
example, there is only one basic structure for conditional programming (if/else/elif), two looping
commands (while and for), and a consistent method of handling errors (try/except) which apply
to all python programs.

Modules

Python relies on modules, that is, self-contained programs which define a variety of functions
and data types, that you can call in order to do tasks beyond the scope of the basic core language
by using the import command..
Object Oriented Programming

Python is a true object-oriented language. The term “object oriented” has become quite a
popular buzzword; such high profile languages as C++ and Java are both object oriented by
design. Many other languages add some object-oriented capabilities, but were not designed to be
object oriented from the ground up as python was.

Namespaces and Variable Scoping

When you type the name of a variable inside a script or interactive python session,
python needs to figure out exactly what variable you’re using. To prevent variables you create
from overwriting or interfering with variables in python itself or in the modules you use, python
uses the concept of multiple namespaces.

Finally, some modules are designed so that you’re expected to have toplevel access to all of the
functions in the module without having to use the module name as a prefix. In cases like this you
can use a statement like:

OPENCV

In the field of Artificial Intelligence, Computer Vision is one of the most interesting and
Challenging tasks. Computer Vision acts like a bridge between Computer Software and
visualizations around us. It allows computer software to understand and learn about the
visualizations in the surroundings. For Example: Based on the color, shape and size determining
the fruit.

Currently, various packages are present to perform machine learning, deep learning and
computer vision tasks. By far, computer vision is the best module for such complex activities.
OpenCV is an open-source library. It is supported by various programming languages such as R,
Python. It runs on most of the platforms such as Windows, Linux and MacOS.
 2. SYSTEM STUDY

2.1 EXISTING SYSTEM

The existing system can be defined as "Given a Portuguese school student dataset[5],
analyze the performance of the student and predict the final grade of the student by considering
previously obtained grade along with other socio-economic factors such as parent's education,
travel time, study time, attendance, family relationship, alcohol consumption, etc. by applying
different machine learning algorithms on the dataset."

2.1.1 DRAWBACKS
• There is a limitation for extracted features’ student performance such as CGPA of
previous semesters and number of credit the student has earned from previous
semesters.
• For this reason, we can use deep learning by its feature extraction to solve
limitation in such systems. As mentioned before, the main difference between
machine learning and deep learning is the features.2.2 PROPOSED SYSTEM
In order to predict the student performance for the next courses from the performance of
previous courses, the research exploits the collected data in the training process for the proposed
method. +en, data will be divided into two sets, according to the date the data was obtained: the
first dataset (data obtained from 2007 to 2016) is used for training, while After collecting the
second dataset (data obtained from 2016 to 2019) is used for testing the proposed method. +e
testing process is used to evaluate the accuracy of the proposed prediction model.

2.2.1 FEATURES

• clear redundant attributes such as course name, lecturer name, and student name.
• clear redundant or noise records such as the courses which have been registered by the
student but its exam, exemption courses, etc. have never been completed.
• some universities ignore courses when the total number of registered student is less than
15. In our case, these ignored courses are consider as noise and will be neglected.
 3. SYSTEM DESIGN AND DEVELOPMENT

3.1 FILE DESIGN

When large volumes of data are being handled, it’s important that the items to be stored
are selected easily and quickly. To accomplish this each data item must have a unique
specification and must be related to other forms or items of data of the same type. The master
file transaction is related to the same type id in the other table while using the primary key in p-
id. A master file in product id is related to another table. There are various product id numbers in
the various numbers in the various numbers of products.

3.2 INPUT DESIGN

The input design is the link between the information system and the user. It comprises
the developing specification and procedures for data preparation and those steps necessary to put
transaction data into a usable form for processing can be achieved by inspecting the computer to
read data from a written or printed document or it can occur by having people keying the data
directly into the system.
Input Design considered the following things:
• What data should be given as input?
• How should the data be arranged or coded?
• The dialog to guide the operating personnel in providing input.
• Methods for preparing input validations and steps to follow when errors occur.
3.3 CODE DESIGN

This overview section contains a list of each table and their relationships with each other
– brief and general. I would like to have a graphic showing the links, similar to what Dave did
in the PowerPoint slides.

The STEWARDS data management system contains three components. They are the
CEAP watershed measurement data, the ARS Methods Catalog, and the STEWARDS System
Support data files.

The CEAP watershed measurement data are located in a suite of data table pairs (Data
table and Data Definition table). The tables are assembled and populated by watershed
personnel. Watershed data will be managed as a collection sites with a common theme as
derived from individual measurement devices, i.e., South Fork Meteorology - Temperature,
rainfall, atmospheric pressure, wind.

Site measurement data will be managed by unique SiteID/DateTime pairs, with

measurements as additional column headings using generic column names mapped to detailed
information in the Definition table.

The tables include:

• Code design – These tables contain the watershed’s measurement data and are described
by the Data Table Definition.
• Data Table Definition Table – This table describes all the measurement code design
provided by the watersheds. The Definition table will maintain the relationship between
the data producer’s data-table specific column names and the ARS Methods Catalog.
The Methods Catalog is currently housed as a MS Access code design and is
accompanied by a suite of tools that may be used to populate the Methods table, Analyte table,
and the Parameter table. These tables include:

• Parameter Table – This is the key table for user querying data using a topic.
• Methods Table – The table captures information describing general and detailed methods
the watershed used to obtain the measurement data. The tables also include links or
pointers to other resources to more fully describe their methods used to capture the
measurement data.
• Analytes Table – The table captures information describing the constituents whose value
is estimated using a method found in the Methods table. There is a one-to-many
relationship between the Methods table and the Analytes table, as there may be more
than one analyte associated with a single method.
• Revision Table – this table is used to capture any revision information that may be
associated with a method.
The STEWARDS System Support data are essential for the system to meet the
requirements of the data providers, system administrator, and end users.

These additional watershed-related tables are used to support query and display
functions in the user interface. Several of these tables are populated by watershed personnel and
maintained by the system administrator.
 These tables include:

• Site Summary table - a system-generated, pre-set collection of information assembled

from watershed-provided data allowing for cross watershed queries.
• Sites table – This table links the sites which the data are collected with the tables that
hold the measurement data.
• SourceTables table – describes the individual measurement code design (TableID ) with
table name, time step, theme, location identifier, date of the last update, andtable author.
• Locations table – This table provide information about the location (watershed) where
the measurement data are collected.
• DataTable-to-Shapefile table – A table that links shapefiles with their associated code
design. In the case of multiple time-steps for a measurement theme, there may be more
than one data table associated with a single shapefile.
• Data Download log – A list of downloaded data and the downloader information.
3.4 OUTPUT DESIGN
A quality output is one, which meets the requirements of the end user and presents the
information clearly. In any system results of processing are communicated to the users and to
other systems through outputs. In output design it is determined how the information is to be
displaced for immediate need and also the hard copy output.
It is the most important and direct source of information to the user. Efficient and
intelligent output design improves the system’s relationship to help user decision-making.

1. Designing computer output should proceed in an organized, well thought out manner;
the right output must be developed while ensuring that each output element is designed so that
people will find the system can be used easily and effectively. When analysis design computer
output, they should Identify the specific output that is needed to meet the requirements.
2. Select methods for presenting information.
3. Create document, report, or other formats that contain information produced by the
system.The output form of an information system should accomplish one or more of the
following objectives.
• Convey information about past activities, current status or projections of the Future.
• Signal important events, opportunities, problems, or warnings.
• Trigger an action.
• Confirm an action.
3.5 DATABASE DESIGN
Data Constraints

All business in the world runs on business data being gathered stored and analyzed.
Business managers determine a set of rules that must be applied to the data being stored to
ensure its integrity.

Types of Data Constraints

There are two types of data constraints that can be applied to data being inserted into a
database table. One type of constraint is called an I/O constraint. The other type of constraint is
called a business rule constraint.

• I/O Constraints:
The input /output data constraint is further divided into two distinctly different constraints.

a)The Primary Key Constraint –

Here the data constraint attached to a column ensures:

• The data entered in the table column is unique across the entire column.
• That none of the cells belonging to the table column are left empty.
b) The Foreign Key Constraint -

Foreign constraint establishes a relationship between records across a master and a detail
table. The relationship ensures.

• Records cannot be inserted in a detail table if corresponding records in the

master table does not exist.
• Records of the master table cannot be deleted if corresponding records in the
detail table exist.
Business Rule Constraints:
The Database allows the application of business rules to table columns. Business
managers determine business rules.

The Database allows programmers to define constraints at:

a) Column Level
b) Table Level
a)Column Level Constraints

If data constraints are defined along with the column definition where creating or
altering a table structure, they are column level constraints.

b)Table Level Constraints

If data constraints are defined after defining all the table columns when creating or
altering a table structure, it is a table level constraint.

Null Value Concepts

A NULL value is different from a blank of zero. NULL values are treated specially by the
database. A NULL value can be inserted into the columns of any data type.

Not Null Constraint Defined at the Column Level

When a column is defined as not null, then that column becomes a mandatory column .It implies
that a value must be entered into the column if the record is to be accepted for storage in the
table.

The Primary Key Constraint

Primary Key Concepts - A primary key in a table used to uniquely identify each row in
the table.A primary key column in a table has special attributes.

It defines the column as a mandatory column i.e. the column cannot be left blank. The
NOT NULL attribute is active.The PRIMARY KEY constraint uniquely identifies each record in
a table. Primary keys must contain UNIQUE values, and cannot contain NULL values.

A table can have only ONE primary key; and in the table, this primary key can consist of
single or multiple columns (fields)The UNIQUE constraint ensures that all values in a column
are different. Both the UNIQUE and PRIMARY KEY constraints provide a guarantee for
uniqueness for a column or set of columns. A PRIMARY KEY constraint automatically has a
UNIQUE constraint.primary key is a column or combination of columns that has the same
properties as a unique constraint.
3.6. SYSTEM DEVELOPMENT

3.6.1 MODULE DESCRIPTION

Registration

In this module user can register themselves. If user is a student, he/she can register by
creating username and password. User can register by filling a little detail about them. If user is
a university, they have to select registration type ‘university’. They also can register by creating
username and password. After registration details are filled accurately user can have their login
username and password.

Add countries

Once admin logged in, admin can see a dashboard in that admin can have a idea about
how many users are registered in , how many countries and how many states are there. As well
as admin can add country and state.

View users

Admin can view how many universities and how many students have registered. Admin
can also delete any account if it is not appropriate. 16IT446 HEPS 12 Admin also can view
student’s education details as well as universities courses.

Account

After registration got complete one can login with help of username and password. They
can go to account module to manage their account and can change in details if any required. In
account user can update their details and also can add new details which is required.

Add education

In this module student can add their education details. Students can add their university
name, course name, percentages, passing year etc. after adding details it will be formed in a table
so that students can as much courses as they have certified.

Add courses

Universities which are already registered can add various courses which are currently
available for students to apply in. In this module university can add course name, duration of that
course, year wise fees structure, requirements to apply in it.

View university
 Students can view universities which are registered in this system and can apply to
courses. Student can see address, state, country of that university as well as contact details like
phone number and email ID. Students can also visit their website. Students can view courses and
can apply to it by selecting to the course and clicking to the apply.

See applied

Both students and universities can see their applied in their profile. students can see how
many courses they have applied for as well as universities also can see how many students
applied to their various courses. After that university can confirm or reject students by their
criteria.
4. TESTING AND IMPLEMENTATION
SYSTEM TESTING

The purpose of testing is to discover errors. Testing is the process of trying to discover
every conceivable fault or weakness in a work product. It provides a way to check the
functionality of components, sub-assemblies, assemblies and/or a finished product. It is the
process of exercising software with the intent of ensuring that the Software system meets its
requirements and user expectations and does not fail in an unacceptable manner. There are
various types of tests.
The following are the main benefits of system testing

• Improved product quality. A comprehensive system testing process ultimately boosts the
product quality. Since an integrated system is tested through multiple test sets in a product
development cycle, it provides a glimpse into whether a product can successfully work
across different platforms and environments.

• Error reduction. Some errors are bound to happen during the development of complex
systems. System testing verifies a system's code and functionality against its requirements,
so errors that aren't detected during integration and unit testing can be exposed during
system testing.

• Cost savings. It can be more time-consuming to fix a system defect that's detected later in
the project lifecycle. Conducting timely and continuous system testing not only reduces
unexpected costs and project delays, but also provides project managers with better budget
control.

• Security. Well-tested products are reliable. They ensure that the tested system doesn't
contain potential vulnerabilities that can put end users and system data at risk of potential
threats.

• Customer satisfaction. System testing offers visibility into the stability of a product at
every stage of development. This builds customer confidence and improves the overall user
experience.

• Easier code modification. System testing can identify code problems during software
development. Fixing older code that has gone into the production environment is much
harder than modifying it while it's still in development.
• Software performance. Performance-based system tests can help understand changes in a
system's performance and behavior, such as memory consumption, central processing unit
utilization and latency. These tests raise red flags if system performance degrades
significantly, enabling developers to take proactive action

TYPES OF TESTS
Unit Testing
Unit testing involves the design of test cases that validate that the internal program logic is
functioning properly, and that program inputs produce valid outputs. All decision branches and
internal code flow should be validated. It is the testing of individual software units of the
application .It is done after the completion of an individual unit before integration. This is a
structural testing that relies on knowledge of its construction and is invasive
Integration Testing

Integration tests are designed to test integrated software components to determine if they
actually run as one program. Testing is event driven and is more concerned with the basic
outcome of screens or fields.

Integration testing is specifically aimed at exposing the problems that arise from the
combination of components.Integration testing is the second level of the software testing process
comes after unit testing.

Functional Test
Functional tests provide systematic demonstrations that functions tested are available as
specified by the business and technical requirements, system documentation, and user manuals.
Functional testing is centered on the following items:
Valid Input : identified classes of valid input must be accepted.
Invalid Input : identified classes of invalid input must be rejected.
Functions : identified functions must be exercised.
Output : identified classes of application outputs must be exercised.
Systems/Procedures: interfacing systems or procedures must be invoked.
Organization and preparation of functional tests is focused on requirements, key
functions, or special test cases. In addition, systematic coverage pertaining to identifying
Business process flows; data fields, predefined processes, and successive processes must be
considered for testing..
White Box Testing
White Box Testing is a testing in which the software tester has knowledge of the inner
workings, structure and language of the software, or at least its purpose. It has a purpose. It is
used to test areas that cannot be reached from a black box level.
Black Box Testing
Black Box Testing is testing the software without any knowledge of the inner workings,
structure or language of the module being tested. Black box tests, as most other kinds of tests,
must be written from a definitive source document, such as specification or requirements
document, such as specification or requirements document
Test strategy and approach
Field testing will be performed manually and functional tests will be written in detail.
Test objectives
 5. FEASIBILITY STUDY

The feasibility of the project is analyzed in this phase and business proposal is put forth
with a very general plan for the project and some cost estimates. During system analysis the
feasibility study of the proposed system is to be carried out. This is to ensure that the proposed
system is not a burden to the company. For feasibility analysis, some understanding of the major
requirements for the system is essential.

A feasibility study is a comprehensive evaluation of a proposed project that evaluates all

factors critical to its success in order to assess its likelihood of success. Business success can be
defined primarily in terms of ROI, which is the amount of profits that will be generated by the
project.

A feasibility study evaluates a project's or system's practicality. As part of a feasibility

study, the objective and rational analysis of a potential business or venture is conducted to
determine its strengths and weaknesses, potential opportunities and threats, resources required to
carry out, and ultimate success prospects. Two criteria should be considered when judging
feasibility: the required cost and expected value.

Three key considerations involved in the feasibility analysis are

• Economical feasibility

• Technical feasibility

• Social feasibility

ECONOMICAL FEASIBILITY

This study is carried out to check the economic impact that the system will have on the
organization. The amount of fund that the company can pour into the research and development
of the system is limited. The expenditures must be justified. Thus the developed system as well
within the budget and this was achieved because most of the technologies used are freely
available. Only the customized products had to be purchased.
TECHNICAL FEASIBILITY

This study is carried out to check the technical feasibility, that is, the technical
requirements of the system. Any system developed must not have a high demand on the
available technical resources. This will lead to high demands on the available technical
resources. This will lead to high demands being placed on the client. The developed system must
have a modest requirement, as only minimal or null changes are required for implementing this
system.

SOCIAL FEASIBILITY

The aspect of study is to check the level of acceptance of the system by the user. This
includes the process of training the user to use the system efficiently. The user must not feel
threatened by the system, instead must accept it as a necessity. The level of acceptance by the
users solely depends on the methods that are employed to educate the user about the system and
to make him familiar with it. His level of confidence must be raised so that he is also able to
make some constructive criticism, which is welcomed, as he is the final user of the system.
 6. APPENDIX

A.SYSTEM ARCHITECTURE

SEQUENCE DIAGRAM
DATA FLOW DIAGRAM
ACTIVITY DIAGRAM
COLLOBARATION DIAGRAM
 B.SAMPLE SOURCE CODE
{

"cells": [

"cell_type": "code",

"execution_count": 28,

"metadata": {},

"outputs": [],

"source": [

"import pandas as pd\n",

"import numpy as np\n",

"import matplotlib.pyplot as plt\n",

"import seaborn as sns\n",

"from scipy.stats import uniform, randint\n",

"\n",

"from sklearn.metrics import auc, accuracy_score, confusion_matrix, mean_squared_error\n",

"from sklearn.model_selection import cross_val_score, GridSearchCV, KFold, RandomizedSearchCV,

train_test_split\n",

"\n",

"from xgboost import XGBClassifier\n",

"from sklearn.tree import DecisionTreeClassifier"

},

"cell_type": "code",

"execution_count": 29,

"metadata": {},

"outputs": [

{
"data": {

"text/html": [

"<div>\n",

"<style scoped>\n",

" .dataframe tbody tr th:only-of-type {\n",

" vertical-align: middle;\n",

" }\n",

"\n",

" .dataframe tbody tr th {\n",

" vertical-align: top;\n",

" }\n",

"\n",

" .dataframe thead th {\n",

" text-align: right;\n",

" }\n",

"</style>\n",

"<table border=\"1\" class=\"dataframe\">\n",

"<thead>\n",

"<tr style=\"text-align: right;\">\n",

"<th></th>\n",

"<th>Year</th>\n",

"<th>10th Marks</th>\n",

"<th>12th Marks</th>\n",

"<th>12th Division</th>\n",

"<th>AIEEE Rank</th>\n",

"<th>College</th>\n",

"</tr>\n",

"</thead>\n",

"<tbody>\n",

"<tr>\n",

"<td>0</td>\n",
"<td>2019</td>\n",

"<td>90</td>\n",

"<td>89</td>\n",

"<td>3</td>\n",

"<td>98</td>\n",

"<td>IIT Bombay</td>\n",

"</tr>\n",

"<tr>\n",

"<td>1</td>\n",

"<td>2015</td>\n",

"<td>95</td>\n",

"<td>92</td>\n",

"<td>2</td>\n",

"<td>100</td>\n",

"<td>IIT delhi</td>\n",

"</tr>\n",

"<tr>\n",

"<td>2</td>\n",

"<td>2018</td>\n",

"<td>91</td>\n",

"<td>80</td>\n",

"<td>6</td>\n",

"<td>260</td>\n",

"<td>IIT kanpur</td>\n",

"</tr>\n",

"<tr>\n",

"<td>3</td>\n",

"<td>2017</td>\n",

"<td>88</td>\n",

"<td>85</td>\n",

"<td>2</td>\n",
"<td>222</td>\n",

"<td>IIT kharagpur</td>\n",

"</tr>\n",

"<tr>\n",

"<td>4</td>\n",

"<td>2016</td>\n",

"<td>89</td>\n",

"<td>84</td>\n",

"<td>1</td>\n",

"<td>600</td>\n",

"<td>IIT guwahati</td>\n",

"</tr>\n",

"</tbody>\n",

"</table>\n",

"</div>"

],

"text/plain": [

" Year 10th Marks 12th Marks 12th Division AIEEE Rank College\n",

"0 2019 90 89 3 98 IIT Bombay\n",

"1 2015 95 92 2 100 IIT delhi\n",

"2 2018 91 80 6 260 IIT kanpur\n",

"3 2017 88 85 2 222 IIT kharagpur\n",

"4 2016 89 84 1 600 IIT guwahati"

},

"execution_count": 29,

"metadata": {},

"output_type": "execute_result"

],

"source": [
"df1=pd.read_csv(\"project-updated.csv\")\n",

"df1.head()"

},

"cell_type": "code",

"execution_count": 30,

"metadata": {},

"outputs": [

"data": {

"text/plain": [

"1004"

},

"execution_count": 30,

"metadata": {},

"output_type": "execute_result"

],

"source": [

"df=df1.copy()\n",

"len(df)"

},

"cell_type": "code",

"execution_count": 31,

"metadata": {},

"outputs": [

{
"name": "stdout",

"output_type": "stream",

"text": [

"['Ahemedabad IT' 'BIT Mesra' 'BITS pilani' 'BMS college of ENGG'\n",

" 'DTU delhi' 'HBUT kanpur' 'IIEST shibpur' 'IIIT hydrabad' 'IIT Bombay'\n",

" 'IIT bhilai' 'IIT delhi' 'IIT goa' 'IIT guwahati' 'IIT hydrabad'\n",

" 'IIT indore' 'IIT jammu' 'IIT jodhpur' 'IIT kanpur' 'IIT kharagpur'\n",

" 'IIT mandi' 'IIT palakkad' 'IIT ropar' 'IIT tirupati'\n",

" 'Jadavpur Univversity' 'KLEF hydrabad' 'MNIT jaipur' 'MNNIT allahabad'\n",

" 'MSIT' 'Manipal IT' 'NIT trichy' 'NIT warangal' 'NMIMS'\n",

" 'Netaji Subhas IT' 'S O A university' 'SRMIST chennai'\n",

" 'SSN college of ENGG' 'University college of ENGG' 'VIT vellore']\n",

"1004\n",

"38\n"

],

"source": [

"colg=np.unique(df['College'])\n",

"print(colg)\n",

"print(len(df))\n",

"print(len(colg))"

},

"cell_type": "code",

"execution_count": 32,

"metadata": {},

"outputs": [],

"source": [

"code=[]\n",
"for i in range(len(colg)):\n",

" code.append(i+1)"

},

"cell_type": "code",

"execution_count": 33,

"metadata": {},

"outputs": [

"data": {

"text/html": [

"<div>\n",

"<style scoped>\n",

" .dataframe tbody tr th:only-of-type {\n",

" vertical-align: middle;\n",

" }\n",

"\n",

" .dataframe tbody tr th {\n",

" vertical-align: top;\n",

" }\n",

"\n",

" .dataframe thead th {\n",

" text-align: right;\n",

" }\n",

"</style>\n",

"<table border=\"1\" class=\"dataframe\">\n",

"<thead>\n",

"<tr style=\"text-align: right;\">\n",

"<th></th>\n",

"<th>Year</th>\n",
"<th>10th Marks</th>\n",

"<th>12th Marks</th>\n",

"<th>12th Division</th>\n",

"<th>AIEEE Rank</th>\n",

"<th>College</th>\n",

"</tr>\n",

"</thead>\n",

"<tbody>\n",

"<tr>\n",

"<td>0</td>\n",

"<td>2019</td>\n",

"<td>90</td>\n",

"<td>89</td>\n",

"<td>3</td>\n",

"<td>98</td>\n",

"<td>9</td>\n",

"</tr>\n",

"<tr>\n",

"<td>1</td>\n",

"<td>2015</td>\n",

"<td>95</td>\n",

"<td>92</td>\n",

"<td>2</td>\n",

"<td>100</td>\n",

"<td>11</td>\n",

"</tr>\n",

"<tr>\n",

"<td>2</td>\n",

"<td>2018</td>\n",

"<td>91</td>\n",

"<td>80</td>\n","<td>6</td>\n",
C.SCREENSHOT
CONCLUSION
 6. CONCLUSION

We used machine learning algorithms for the prediction. We found that the logistic
regression algorithm gives the highest accuracy with 73.19%. Since we are considering the
percentages and average score of the Maths and the Science subject, we have an edge over
other prediction methods used for the higher education access prediction. Our system can
give the precise prediction of the stream to the user i.e. student. Even if the student is getting
good marks in aptitude but not has a good percentage and the average score then the
prediction will vary according to the percentages and average. So, this system can help a
student in the stream prediction i.e. Science, Commerce, and Arts. This system can guide the
user to take the correct decision. In the future, we aim to make a system that can store the
data of the students and admin. The system can have a login and signup included. We can
look to improve the accuracies of the algorithms used. We can do feature scaling to improve
the accuracies.
 BIBLIOGRAPHY
1.Baradwaj, Brijesh & Pal, Saurabh. (2011). Mining Educational Data to Analyze Students'
Performance. International Journal of Advanced Computer Science and Applications.
2. 63-69. 10.14569/IJACSA.2011.020609. [2] Dhilipan, J., Vijayalakshmi, N., Suriya, S., &
Christopher, A. (2021). Prediction of Students Performance using Machine learning. IOP
Conference Series: Materials Science and Engineering, 1055(1), 012122.doi:10.1088/1757-
899x/1055/1/012122.
[3] S. Huang and N. Fang, "Work in progress: Early prediction of students' academic
performance in an introductory engineering course through different mathematical modeling
techniques," 2012 Frontiers in Education Conference Proceedings, 2012, pp. 1-2, doi:
10.1109/FIE.2012.6462242.
[4] J. Gamulin, O. Gamulin and D. Kermek, "Comparing classification models in the final exam
performance prediction," 2014 37th International Convention on Information and
Communication Technology, Electronics and Microelectronics (MIPRO), 2014, pp. 663-668,
doi: 10.1109/MIPRO.2014.6859650.
[5] https://archive.ics.uci.edu/ml/datasets/student+performance
[6] Ajay Ohri (2017, Feb 16). Popular regression algorithms [Online]. Available:
https://www.jigsawacademy.com/popular-regression-algorithms-ml/ accessed on 25.10.2021. [7]
A. M. Shahiri, W. Husain, and N. A. Rashid, “A Review on Predicting Student’s Performance
Using Data Mining Techniques,” in Procedia Computer Science, 2015.
[8] P. Guleria, N. Thakur, and M. Sood, “Predicting student performance using decision tree
classifiers and information gain,” Proc. 2014 3rd Int. Conf. Parallel, Distrib. Grid Comput.
PDGC 2014, pp. 126–129, 2015.
[9] Z. Liu and X. Zhang. Prediction and analysis for students’ marks based on decision tree
algorithm. In 2010 Third International Conference on Intelligent Networks and Intelligent
Systems, page 338341, Nov 2010
[10] P. Kaur and W. Singh. Implementation of student sgpa prediction system (ssps) using
optimal selection of classification algorithm. In 2016 International Conference on Inventive
Computation Technologies (ICICT), volume 2, page 18, Aug 2016.