1. Abstract

Campus placement is an important milestone for students completing their higher education. Companies often evaluate students based on academic performance, skills, and work experience before offering job opportunities. Predicting whether a student is likely to get placed can help students understand their readiness and improve their preparation.

This project focuses on building a Campus Placement Prediction Web Application using machine learning techniques. The system takes several student attributes as input, such as academic scores, specialization, work experience, and degree details, and predicts whether the student is likely to get placed in a company.

The workflow of the project includes data collection, preprocessing, feature selection, model training, hyperparameter tuning, and model deployment. The machine learning model is trained using placement dataset information obtained from Kaggle. After training, the model is saved using a pickle file and integrated with a Flask-based web application.

The application allows users to enter their academic details through a form and receive a prediction regarding their placement chances. Finally, the web application is deployed on Microsoft Azure Cloud Services to make it accessible online. This project demonstrates the integration of machine learning, web development, and cloud deployment to build a practical data science application.

2. Objectives

The main objectives of this project are:

1. To analyse campus placement data and identify important factors affecting placements.
2. To build a machine learning model that predicts whether a student will get placed.
3. To preprocess and clean the dataset for accurate model training.
4. To perform feature selection and hyperparameter tuning for improved model performance.
5. To develop a user-friendly web interface using Flask.
6. To integrate the machine learning model with the web application.
7. To deploy the application on Microsoft Azure cloud platform.

2.Existing System

In the traditional system, placement prediction is mainly based on manual evaluation of student academic records and interview performance. Placement officers and recruiters usually analyse students’ academic percentages and skills individually.

Limitations of the Existing System

1. Manual evaluation takes a lot of time.
2. Difficult to analyse large datasets of student records.
3. Predictions are often subjective and may vary between recruiters.
4. Lack of automated systems for placement prediction.
5. Students do not have a clear idea about their placement chances beforehand.

These limitations highlight the need for an automated system that can analyse student data and predict placement outcomes efficiently.

3.Proposed System

The proposed system uses machine learning techniques to predict campus placements automatically.

In this system:

1. A dataset containing student academic details and placement outcomes is used.
2. Data preprocessing techniques are applied to handle missing values and generate new features.
3. Important features are selected for training the machine learning model.
4. Hyperparameter tuning is performed to improve the accuracy of the algorithm.
5. The trained model is saved using a pickle file.
6. A Flask-based web application is developed where users can input student details.
7. The web application uses the trained model to predict placement results.
8. The final application is deployed on Microsoft Azure Cloud Service.

This system provides quick and accurate placement predictions based on student data.

4.Implementation Procedure

The implementation of the project is carried out in the following steps:

Step 1: Data Collection

The placement dataset is collected from Kaggle, which contains information about students’ academic performance, work experience, and placement status.

Step 2: Data Loading

The dataset is loaded into data frames using Python libraries such as Pandas.

 Step 3: Data Preprocessing

Data preprocessing includes:

1. Handling missing or null values
2. Cleaning the dataset
3. Generating new features if required
4. Preparing the dataset for machine learning algorithms

Step 4: Exploratory Data Analysis (EDA)

Exploratory data analysis is performed to:

1. Understand relationships between different variables
2. Identify patterns in placement data
3. Extract meaningful insights from the dataset

Step 5: Feature Selection

Important features that influence placement are selected, such as:

1. Academic percentages
2. Work experience
3. Degree specialization
4. MBA percentage

These features are used as inputs for the machine learning model.

Step 6: Model Training

Machine learning algorithms are applied to train the model using the selected features. Hyperparameter tuning is used to find the best parameters for the algorithm to improve prediction accuracy.

Step 7: Model Saving

After training, the model is saved using a pickle file (.pkl) so that it can be reused without retraining.

Step 8: Web Application Development

A Flask web application is created where users can enter details such as:

1. Gender
2. Specialization
3. Work experience
4. SSC percentage
5. Higher secondary percentage
6. Degree percentage
7. MBA percentage

The application sends these inputs to the trained model to generate predictions.

Step 9: Prediction Output

The system predicts whether the student is likely to get placed or not and displays the result on the web interface.

If the student is not eligible, the system also provides tips to improve placement chances.

Step 10: Deployment

The entire application is deployed on Microsoft Azure Cloud Service, making it accessible online through a web URL.

6. Software Requirements

The software required for this project includes:

1. Python Programming Language
2. Jupyter Notebook / VS Code
3. Flask Framework
4. Machine Learning Libraries (Scikit-learn)
5. Pandas and NumPy
6. Microsoft Azure Cloud Platform
7. Web Browser

7. Hardware Requirements

The minimum hardware requirements are:

1. Processor: Intel i3 or higher
2. RAM: 4 GB minimum (8 GB recommended)
3. Storage: 256 GB or higher
4. System: Laptop or Desktop computer

8.Advantages of the Project

1. Provides an automated system for placement prediction.
2. Helps students understand their chances of getting placed.
3. Saves time compared to manual analysis.
4. Integrates machine learning with a web application.
5. Provides real-time predictions based on student data.
6. Deployed on cloud platform for easy accessibility.
7. Helps students improve their preparation for campus placements.