0% found this document useful (0 votes)
14 views24 pages

App Report Group 22

Uploaded by

hlmahekagarwalla
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
14 views24 pages

App Report Group 22

Uploaded by

hlmahekagarwalla
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 24

ADMISSION PREDICTOR

21CSC203P/ADVANCED PROGRAMMING
PRACTICE PROJECT REPORT

Submitted by

SAMIYA BAKSHI RA2311003020087

AMRITA SINHA RA2311003020105


Under the guidance of

Ms. P. MALATHI
(Assistant Professor, Department of Computer
Science and Engineering)

in partial fulfilment for the award of the degree

of

BACHELOR OF TECHNOLOGY
in

COMPUTER SCIENCE AND ENGINEERING

Of

FACULTY OF ENGINEERING
AND TECHNOLOGY

SRM INSTITUTE OF SCIENCE AND


TECHNOLOGY RAMAPURAM, CHENNAI

1
SRM INSTITUTE OF SCIENCE AND
TECHNOLOGY
(Deemed to be University U/S 3 of UGC Act, 1956)

BONAFIDE CERTIFICATE

Certified that this project report titled ADMISSION PREDICTOR is the


bonafide work of SAMIYA BAKSHI (RA2311003020087) and AMRITA
SINHA (RA2311003020105) who carried out the project work under my
supervision. Certified further, that to the best of my knowledge the work reported
herein does not form any other project report or dissertation on the basis of which
a degree or award was conferred on an occasion on this or any other candidate.

SIGNATURE SIGNATURE

Ms. P. MALATHI Dr. K. RAJA, M.E., Ph.D.,

Assistant Professor Professor and Head


Computer Science and Engineering, Computer Science and Engineering,
SRM Institute of Science and SRM Institute of Science and
Technology, Ramapuram, Chennai. Technology, Ramapuram, Chennai.

Submitted for the project viva-voce held on Technology,


at SRM Institute of Science and
Ramapuram, Chennai.

2
SRM INSTITUTE OF SCIENCE AND
TECHNOLOGY

RAMAPURAM, CHENNAI

DECLARATION

We hereby declare that the entire work contained in this project report titled
ADMISSION PREDICTOR has been carried out by SAMIYA BAKSHI
(RA2311003020087) and AMRITA SINHA (RA2311003020105) at SRM
Institute of Science and Technology, Ramapuram, Chennai, under the guidance
of MALATHI, Associate professor, Department of Computer Science and
Engineering.

Place: Chennai SAMIYA BAKSHI


Date: AMRITA SINHA

3
ABSTRACT

The web application uses machine learning to predict a student's chances of being
admitted to a postgraduate program at Stanford University. It functions by taking
various academic and test-related inputs, such as GRE (Graduate Record
Examination) and TOEFL (Test of English as a Foreign Language) scores.
Additional inputs could include undergraduate GPA, research experience, letters of
recommendation etc.

Once the input data is submitted, the application analyzes it using a machine learning
model that has been trained on historical admission data. This model identifies
patterns in past admission decisions, learning which factors (such as high GRE scores
or exceptional GPAs) are most closely linked to successful admission outcomes.
After processing the student's data, the system outputs a probability score or a
likelihood percentage, which represents the chance of getting accepted into Stanford's
postgraduate programs.

The goal of the application is to give students a data-driven evaluation of their


application potential, allowing them to plan their efforts more strategicall

4
TABLE OF
CONTENTS

Page. no
ABSTARCT 4
LIST OF FIGURES 6
1 Introduction 7

1.1 Introduction 7

1.2 Problem 7

1.3 Objectives 8

1.4 Scope and Motivation 9

2 Existing System 10

3 Flow Diagram and Proposed Methodology 12

4 Implementation (Java and Python) 19

5 Result and Discussion 28

6 Conclusion 31

7 References 34

5
LIST OF FIGURES

3.1 Flow Diagram for Python Code 12


3.2 Flow Diagram for Java Code 16
5.1 Result in Python 28
5.2 Result in Java 30

6
CHAPTER 1
INTRODUCTION

1.1 INTRODUCTION

Academic performance is a crucial aspect of student life, and tracking it


accurately is essential for understanding progress and areas for improvement.
Our web application is a machine learning-powered admission predictor. The
website predicts the probability of a student getting accepted into a postgraduate
degree at Stanford University.

Utilizing a linear regression model, the app achieves an impressive accuracy of


91%.The prediction is based on key features such as GRE scores, TOEFL
scores, CGPA, university rankings, SOP and LOR scores, and research
publication status. It uses the Graduate Admissions Prediction Kaggle dataset,
employing scikit-learn and linear regression for accurate predictions.

The application's prediction output is a probability score, giving students a clear


understanding of their chances of acceptance based on their academic profile
and additional factors. This tool could be a critical aid for students aiming to
optimize their applications by highlighting areas that could be improved for
better chances.

1.2 PROBLEM STATEMENT:


7
In today's highly competitive academic landscape, students applying to Ivy League
schools face significant uncertainty about their chances of admission due to the
holistic and multifaceted nature of the selection process. Applicants often struggle to
assess how their academic achievements, extracurricular activities, and personal
experiences will be evaluated by admissions committees.

The Challenge:
To create a data-driven, web-based platform that leverages machine learning and
advanced data analytics to:
1. Accurately predict a student's probability of admission to Ivy League schools.
2. Provide personalized insights and actionable recommendations based on
academic performance, extracurricular involvement, personal achievements,
and other key factors.
3. Help students optimize their applications and make informed decisions by
highlighting areas that require improvement and simulating potential changes
to their profiles.

The platform would bridge the gap between students' application profiles and the
admission expectations of elite institutions, empowering applicants to strategize more
effectively and improve their chances of success.

8
1.3 OBJECTIVES:

The primary objective of this project is to develop a predictive model that helps
prospective students estimate their chances of being admitted to Stanford
University’s postgraduate programs. By analyzing data collected from 400 surveyed
applicants, the project aims to explore key factors that significantly influence
admission decisions and to build a machine learning model that can accurately
predict the likelihood of acceptance.
Stanford University, like many elite institutions, evaluates applicants based on a
range of academic, extracurricular, and personal achievements. These aspects include
but are not limited to standardized test scores (GRE, TOEFL), undergraduate GPA,
university ranking, letters of recommendation (LOR), statement of purpose (SOP),
and research experience. For applicants, preparing for and applying to a master's
program is not only time-consuming but also a costly endeavor, and the uncertainty
of admission adds stress to the decision-making process.

Key Objectives:

1. Data Exploration and Analysis:

 Examine the data provided by the 400 surveyed applicants to gain a deeper
understanding of the features that influence admission decisions.
 Identify the most critical factors that contribute to a student's success in
gaining admission (e.g., GRE scores, GPA, research experience).

2. Feature Selection:

 Determine which aspects of a student’s profile carry the most weight in


Stanford’s admissions process.
 Use statistical methods or machine learning techniques to rank the
importance of different features (e.g., GRE vs. GPA, SOP vs. LOR).

9
3. Model Development and Comparison:

 Apply different machine learning algorithms to predict admission


probability, such as linear regression, decision trees, random forests, or
neural networks.
 Evaluate the models to identify which one offers the highest predictive
accuracy while balancing interpretability.
 The goal is to find the most accurate model that students can use to
predict their chances of admission with confidence.

4. Empowering Students:

 Provide prospective students with data-driven insights into their


admission probabilities, allowing them to gauge their competitiveness
before applying.
 Help students make more informed decisions about whether to proceed
with an application based on their academic strengths and weaknesses.
 Offer recommendations on how students can enhance their profiles (e.g.,
improving standardized test scores, gaining more research experience) to
increase their chances of acceptance.

By achieving these objectives, the project will offer a useful decision-making tool for
students. They can estimate their capacities and chances before committing to the
extensive time, effort, and financial investment involved in applying for a master's
degree. This predictive tool will serve as a guide, helping students decide if they
should proceed with their applications or focus on improving specific areas of their
academic profiles first.

1
0
1.4 SCOPE AND MOTIVATION:

SCOPE
The scope of building a website that predicts the chances of getting into an Ivy
League institute for graduation encompasses several components:

1. User Input:
• Academic records (GPA, standardized test scores like SAT/ACT).
• Extracurricular activities (clubs, sports, community service).
• Personal achievements (awards, recognitions).
• Letters of recommendation and personal statement evaluations.
• Demographics (geographical location, socioeconomic background).

2. Data Collection and Analysis:


• Utilize historical data from past applicants to Ivy League schools.
• Implement machine learning models that analyze correlations between
applicants profiles and acceptance rates.
• Continuously update the dataset with new admissions data to improve prediction
accuracy.

3. Prediction Algorithm:
• Develop algorithms that factor in weighted criteria based on the importance Ivy
League schools place on various elements of the application (e.g., academic
performance, extracurriculars, essays).
• Offer percentage-based predictions or risk assessments.

4. User Interface (UI):


• Create a user-friendly interface for data entry.
• Provide detailed feedback on how individual factors contribute to the overall
prediction.
• Suggest actionable improvements (e.g., areas to focus on to increase admission
chances).

1
1
MOTIVATION

1.Addressing Applicant Anxiety:


• Applying to Ivy League schools can be an overwhelming process, with
significant uncertainty about the likelihood of acceptance.
• A prediction tool can help reduce this anxiety by providing some clarity and
guidance.

2. Improving Accessibility:
• Many students may not have access to high-quality college counseling.
• This website can democratize access to insights typically available through
expensive private counselors, especially for underrepresented or low-income
applicants.

3. Data-Driven Decision Making:


• By using data analytics, students can make more informed decisions about
where to apply, how to strengthen their applications, and what factors might
be most critical in their profiles.

4. Improving Accessibility:
• Many students may not have access to high-quality college counseling.
• This website can democratize access to insights typically available through
expensive private counselors, especially for underrepresented or low-income
applicants.

5.Data-Driven Decision Making:


• By using data analytics, students can make more informed decisions about
where to apply, how to strengthen their applications, and what factors might be
most critical in their profiles.

1
2
CHAPTER 2
EXISTING SYSTEM

In the realm of education technology, there are several platforms and tools that offer
similar services for predicting admission chances to universities like Stanford. These
existing systems generally fall into two categories: manual counseling services and
automated machine learning-based prediction platforms.

1. Manual Admission Counseling Services:

 Traditional Counseling: Many students rely on educational consultants or


guidance counselors to provide them with advice about their chances of
admission based on their profiles. These services are largely subjective and
depend on the experience of the counselor rather than on data-driven insights.
 Limitations:
o Subjectivity: Counselors offer personalized advice but are often limited
by their experience and perspective.
o High Costs: These services are often expensive, especially for
international students.
o Lack of Scalability: Counseling is typically 1:1, limiting the number of
students that can be helped in a short period.

2. Automated Online Admission Predictors:

 Existing Tools: There are several online platforms that offer basic probability
estimates for admission to different universities, including both free and paid
tools.

11
 Limitations:
o Lack of Comprehensive Input: Many of these systems focus only on a
few data points like GPA and test scores, without taking into account the
full profile of a student (e.g., SOP, LOR, research).

o Generic Prediction Models: Often these systems use rudimentary scoring


algorithms or linear regressions, which are not optimized for more
complex relationships between different factors like research experience
or school rankings.

o Limited Insights: Most tools only provide a rough admission percentage


and do not give detailed recommendations on how to improve a
student’s chances.

Gaps in Existing Systems:


Despite the presence of these tools, there are several gaps that make it difficult for
students to get accurate and detailed insights:
1. Holistic Admissions: Top-tier schools like Stanford use a holistic admissions
process, meaning that they consider a range of factors, from academic
performance to personal achievements. Many existing tools don’t fully
incorporate factors like SOP quality, LOR strength, or research experience,
which are critical for graduate applications.
2. Accurate Predictions: Most of the tools focus on high school or undergraduate
admissions and are not as tailored to the competitive nature of graduate
admissions, especially for elite schools like Stanford.
3. Data-Driven Insights: Few systems use sophisticated machine learning models
trained on large datasets to give precise and individualized predictions. Many
tools are based on outdated, static data or oversimplified models.

12
CHAPTER 3
FLOW DIAGRAM AND PROPOSED METHODOLOGY

3.1 FLOW DIAGRAM IN PYTHON

Fig 3.1 Flow Diagram

PROPOSED METHODOLOGY
This methodology outlines the underlying processes, algorithms, and
techniques used at each stage to ensure a smooth workflow in Python. Each part
builds on the previous step, leading from data collection to model deployment
and prediction.
Step 1: Data Collection and Input
1. User Input:
• Collect relevant data from students, such as GRE scores, TOEFL scores,
CGPA, University ranking, SOP, LOR, and Research experience.
• These data points are the input features for predicting admission
probability.
• The student inputs their data via the web interface (e.g., form
submission).
13
2. Data Collection from Dataset:
• Use a historical admissions dataset (like the Graduate Admissions
Prediction Kaggle dataset) to train the model. This dataset contains
similar features to those provided by the student.

Step 2: Data Preprocessing


Data preprocessing is essential to ensure that the model receives clean, normalized,
and consistent data for effective learning.

1. Handling Missing Data:


• Remove or fill any missing values (e.g., using fillna() in pandas). This
ensures there are no gaps in the data that would disrupt the model’s
training.

2. Feature Scaling:
• Standardize numerical values such as GRE, TOEFL, and CGPA, as they
may have different scales (GRE out of 340, TOEFL out of 120, CGPA
out of 10, etc.). Feature scaling helps ensure that one feature doesn't
dominate others due to its larger scale.

Step 3: Prediction
Once the model is trained and evaluated, it can be used to make predictions for new
users.

1. User Data Input:


• The student’s input (e.g., GRE, TOEFL, CGPA, etc.) is processed
similarly to the training data, including scaling and encoding.
2. Make a Prediction:
• The trained model is used to predict the admission probability for the
student's profile.

Step 4: Output and Recommendations


The final output involves displaying the prediction and providing actionable insights
to the student.

1. Display Results:
• The predicted admission probability is displayed to the user via the
web interface. This is usually a percentage score representing the
likelihood of acceptance.
• Example: "You have a 75% chance of getting admitted to Stanford."

14
3.2 FLOW DIAGRAM IN JAVA

Fig 3.2 Flow Diagram for Java

15
PROPOSED METHODOLOGY

The Java implementation follows the same overall steps:


1. Data Collection and Input
2. Data Preprocessing
3. Model Selection and Training
4. Prediction
5. Output and Recommendations

Step 1: Data Collection and Input


1. User Input:
• The user enters their data (GRE, TOEFL, CGPA, etc.) via a web form in
a Java-based web application (e.g., using Spring Boot or Java Servlets).
• Input data is collected as part of an HTTP request.

Step 2: Data Preprocessing


• In Java, data preprocessing can be done using frameworks like Apache
Commons Math or Weka for machine learning tasks.

Step 3: Data Preprocessing


• In Java, data preprocessing can be done using frameworks like Apache
Commons Math or Weka for machine learning tasks.

Step 4: Prediction
Once the model has been trained, it can be used to predict the admission
probability for a new student.
• User Data Input:
Take the input from the user, preprocess it (e.g., scale it), and use the trained
model to make predictions.

16
• Make Predictions:
The model will output the admission probability based on the input.

Step 5: Output and Recommendations


1. Display Results:
• Display the predicted admission probability in the user interface (UI),
using a Java web framework like Spring Boot or JavaServer Pages
(JSP).

Java Libraries :
 Weka: A popular library for data mining and machine learning in Java.
• Includes various classifiers, regressors, and clustering algorithms.
• Use Case: Can be used for both data preprocessing and model training.

 Smile (Statistical Machine Intelligence and Learning Engine): A machine


learning library that provides a comprehensive set of algorithms for
classification, regression, clustering, and more.
• Use Case: Suitable for training models such as linear regression,
decision trees, and neural networks.

 Apache Commons Math: Useful for mathematical operations and basic


regression analysis.

17
CHAPTER 4
IMPLEMENTATION (JAVA AND PYTHON)

4.1 IMPLEMENTATION IN JAVA

18
4.2 IMPLEMENTATION IN PYTHON

29
CHAPTER 5
RESULT AND DISCUSSION

5.1 RESULT IN PYTHON:


Output of the Program:

Fig 5.1.1 Result in Python

21
0
CHAPTER 6

CONCLUSION

The Stanford University Admission Predictor project successfully utilizes


machine learning techniques to predict a student's probability of admission
based on key academic and personal features. By leveraging data such as
GRE scores, TOEFL scores, CGPA, university ranking, SOP, LOR scores,
and research experience, the system offers applicants a realistic assessment
of their chances for postgraduate admission.

The project addresses the need for a data-driven approach in simplifying


the complex and often stressful admission process. Students benefit from
this predictive tool by receiving insights into their admission probabilities,
which can help them make informed decisions about applying. This
system, powered by a linear regression model, achieved an accuracy of
91%, demonstrating its effectiveness in making reliable predictions.

Through preprocessing, feature scaling, model training, and evaluation, the


application demonstrates the power of machine learning in educational
domains. Additionally, the platform is designed to provide personalized
recommendations to students on how to improve their profiles, further
enhancing its utility.

In conclusion, the project showcases how artificial intelligence and data


science can assist prospective students in their academic journey, saving
time, resources, and effort. As future work, the system can be extended to
include more advanced algorithms, a larger dataset, and predictions for
multiple universities, making it even more comprehensive for students
around the world.

31
1
CHAPTER 7

REFERENCE

● https://docs.streamlit.io/library

● https://towardsdatascience.com/a-complete-guide-to-streamlit-for-beginners-
dc43b27fc7e7

● https://medium.com/swlh/building-a-machine-learning-web-app-with-
streamlit-330e7d7c4931

● https://www.datacamp.com/community/tutorials/deploy-machine-learning-
model-streamlit

● https://www.analyticsvidhya.com/blog/2020/09/streamlit-a-powerful-library-
for-data-scientists/

31
2

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy