Description
Student Placement Prediction using Machine Learning
Abstract:
The placement of scholars is every one of the vital activities in academic establishments. Admission and name of establishments primarily depend? on placements. Hence all institutions strive to Strengthen placement departments. In this study, the objective is to analyze the previous year’s student data and use it to predict the placement chance of the current students. This model is proposed with an algorithm to predict the same. Any assistance in this particular area will have a positive impact on an institution’s ability to place its students. This will always be helpful to both the students, as well as the institution. In this study, the objective is to analyze the previous year’s student data and use it to predict the placement chance of the current students. This model is proposed with an algorithm to predict the same. Data pertaining to the study were collected from the same institution for which the placement prediction is done, and also suitable data pre-processing methods were applied. This proposed model is also compared with other traditional classification algorithms such as Decision tree and Random forest with respect to accuracy. From the results obtained it is found that the proposed algorithm performs significantly better in comparison with the other algorithms mentioned. Student Placement Prediction using Machine Learning
Objective:
The main objective of this paper is to analyze previous year’s student’s historical data and predict placement possibilities of current students and aid to increase the placement percentage of the institutions. Student Placement Prediction using Machine Learning
Problem definition:
The problem is to collect previous students’ data and analyze those data for new students in the institute for prediction purposes. Student Placement Prediction using Machine Learning
Existing System:
They used WEKA as the data mining tool to build the model using a random tree algorithm. They also used ID3, Bayes Net, RBF network, J48, and algorithms on the student data set. They resolved that the RT (Random Tree) algorithm is more accurate with 73% for the classification/prediction of the model. The accuracy using ID3 and J48 is 71%. Bayes Net is 70% accurate and 65% accurate using RBF network algorithms
It has been observed that most of the approaches are rooted in the decision tree algorithm. However, they emphasize on the algorithms used in order to increase the accuracy are Fuzzy logic and K nearest neighbor. Student Placement Prediction using Machine Learning
Proposed System:
This model is proposed with an algorithm to predict the same. Data pertaining to the study were collected from the institution for which the placement prediction is done, and also suitable data pre-processing methods were applied. This proposed model is also compared with other traditional classification algorithms such as Existing techniques, Decision trees, SVM, and Random forest with respect to accuracy, precision, and recall.
Advantage:
- Does the proposal aim to analyze students? demographic data, study-related details, and psychological characteristics in terms of final state to figure out whether the student will be placed or not.
- The proposed algorithm performance significantly we compared and stated better one. Student Placement Prediction using Machine Learning
System Architecture:
Student Placement Prediction using AI
PYTHON ENVIRONMENT
Python is available on a wide variety of platforms including Linux and Mac OS X. Let’s understand how to set up our Python environment.
REQUIREMENTS ANALYSIS
SOFTWARE REQUIREMENTS
- Python
- Anaconda Navigator
- Python built-in modules
- Numpy
- Pandas
- Matplotlib
- Sklearn
- Seaborn
Customer Reviews
There are no reviews yet.