Scholarlink

In today’s world of education, making informed decisions about selection is vital, especially for students aspiring to enter the field of engineering. The process can be tedious as students are often stuck with a lack of proper information and guidance, leading to confusion during the admission process. In response to this challenge, the proposed model in this paper provides a best-suited college for a student based on category, gender, rank, and percentile by taking input from the user, by collecting datasets from the Directorate of Technical Education (DTE) site and converting them into CSV files by transforming them into queries. The preprocessing is done by removing null values, dropping unnecessary columns, label encoding, etc. Various algorithms such as linear regression, random forest, and AdaBoost are tested on the dataset. The model has been trained on a dataset with different training–testing ratios. The AdaBoost algorithm has achieved the highest accuracy of 91.74% among all other tested algorithms. The AdaBoost machine learning model is a combination of various weak classifiers resulting in strong classifiers. Several iterations are performed by varying weights. Also, other parameters such as n_estimators, learning rate, training, and testing ratio are varied to get the highest accuracy which will generate the list of colleges.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Maharashtra Engineering College Admission Prediction—A Solution Using Ensemble Machine Learning Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Pragati Mundhe,
  • Omkar Mohare,
  • Chaitanya Gabhane,
  • Abdul Muqueet Sahil,
  • Usha Verma

摘要

In today’s world of education, making informed decisions about selection is vital, especially for students aspiring to enter the field of engineering. The process can be tedious as students are often stuck with a lack of proper information and guidance, leading to confusion during the admission process. In response to this challenge, the proposed model in this paper provides a best-suited college for a student based on category, gender, rank, and percentile by taking input from the user, by collecting datasets from the Directorate of Technical Education (DTE) site and converting them into CSV files by transforming them into queries. The preprocessing is done by removing null values, dropping unnecessary columns, label encoding, etc. Various algorithms such as linear regression, random forest, and AdaBoost are tested on the dataset. The model has been trained on a dataset with different training–testing ratios. The AdaBoost algorithm has achieved the highest accuracy of 91.74% among all other tested algorithms. The AdaBoost machine learning model is a combination of various weak classifiers resulting in strong classifiers. Several iterations are performed by varying weights. Also, other parameters such as n_estimators, learning rate, training, and testing ratio are varied to get the highest accuracy which will generate the list of colleges.