INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
A Real-time Web Application using Machine Learning for Predicting University Dropouts
Authors Name:
Sushmitha K
, Dr. Shivamurthy R C
Unique Id:
IJSDR2308010
Published In:
Volume 8 Issue 8, August-2023
Abstract:
In order to prevent dropouts from occurring, it is necessary to identify pupils who are likely to stop attending school or a college. This field of study is crucial because it enables educational institutions to help difficult students and potentially increase the likelihood that they will graduate from college. Dropout rates from engineering colleges place a significant strain on a nation's citizens' ability to pursue higher education and build successful careers. The prosperity of a nation rests,on its capacity to produce graduates from higher education who can advance the nation. Various institutions are looking to artificial intelligence's (AI) potential to anticipate dropout as early as feasible to help solve the dropout problem. Because it can be challenging to obtain personal information and does so with privacy concerns, schools must be dependent on the theoretical statistics of their students to build precise and dependable extrapolative algorithms. The goal of this effort is to construct the finest prediction model based just on the academic information; therefore it must have the greatest ability to infer knowledge. Comprehensions and forecasting skills to boost academic results is very important for any student to achieve greater heights. On relevant datasets, machine learning algorithms can be used to find patterns, trends, and important variables that influence the achievement of students. Many students61.8% are High level. 38.2% are in the low level. In total, there are 36.5% female students and 63.5% male pupils. Just 5% of female students are in low level classes. So, the academic growth of female students is higher than that of male students. In comparison, female students engage significantly more in educational events than their male counterparts. According to our observation, this means that female students perform better than male pupils. In this project, machine learning is being used to forecast the student's performance. Decision Tree Algorithm (DT), Random Forest Classifier (RFC), and Logistic Regression Algorithm (LR) constitute the model. Here, we developed a web application that will analyze user input to figure out if a student will drop out of university or not.
Keywords:
Dropout, Machine Learning, Flask, Web Application
Cite Article:
"A Real-time Web Application using Machine Learning for Predicting University Dropouts ", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 8, page no.63 - 67, August-2023, Available :http://www.ijsdr.org/papers/IJSDR2308010.pdf
Downloads:
000338720
Publication Details:
Published Paper ID: IJSDR2308010
Registration ID:208087
Published In: Volume 8 Issue 8, August-2023
DOI (Digital Object Identifier):
Page No: 63 - 67
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn