🎓 Student Placement Prediction

---

📌 Overview

Student placement is one of the most important aspects of academic institutions.
This project uses Machine Learning to predict whether a student will be Placed or Not Placed based on academic performance and other attributes.

The system analyzes historical placement data and learns patterns that influence employability.

The goal is to help:

🎓 Students understand their placement chances
🏫 Colleges improve placement training
💼 Recruiters identify potential candidates

---

🚀 Project Highlights

✔ Real-world campus placement dataset
✔ Complete ML pipeline implementation
✔ Data preprocessing and feature engineering
✔ Multiple machine learning models
✔ Model performance evaluation
✔ Data visualization and insights

---

🧠 Machine Learning Workflow

Raw Dataset
     │
     ▼
Data Cleaning
     │
     ▼
Exploratory Data Analysis
     │
     ▼
Feature Engineering
     │
     ▼
Model Training
     │
     ▼
Model Evaluation
     │
     ▼
Placement Prediction

---

📂 Project Structure

Student-Placement-Prediction
│
├── dataset
│   └── Placement_Data_Full_Class.csv
│
├── notebooks
│   └── student_placement_prediction.ipynb
│
├── REPORT.md
│
├── README.md
│
└── LICENSE

---

📊 Dataset Information

The dataset contains student academic records and placement results.

Key Features

Feature	Description
gender	Student gender
ssc_p	Secondary school percentage
hsc_p	Higher secondary percentage
degree_p	Degree percentage
degree_t	Degree specialization
workex	Work experience
etest_p	Employability test score
specialisation	MBA specialization
mba_p	MBA percentage
salary	Salary offered
status	Placement status

Target Variable:

status → Placed / Not Placed

---

🔍 Exploratory Data Analysis

EDA helps understand:

• Placement distribution
• Academic performance impact
• Salary trends
• Feature correlations

Example Visualization

sns.countplot(x="status", data=df)
plt.title("Placement Distribution")
plt.show()

---

🤖 Machine Learning Models Used

Several classification algorithms were applied:

Model	Purpose
Logistic Regression	Baseline classification
Decision Tree	Rule-based prediction
Random Forest	Ensemble learning
Support Vector Machine	Advanced classification

---

📈 Model Evaluation Metrics

To measure model performance we used:

✔ Accuracy
✔ Precision
✔ Recall
✔ F1 Score
✔ Confusion Matrix

Example:

from sklearn.metrics import accuracy_score

accuracy_score(y_test, y_pred)

---

📊 Model Comparison

Model	Accuracy
Logistic Regression	High
Decision Tree	Moderate
Random Forest	Best
SVM	Competitive

Random Forest generally performs the best because it combines multiple decision trees.

---

💡 Key Insights

Important factors influencing student placement include:

• Degree percentage
• Employability test score
• Work experience
• MBA specialization

Students with higher academic performance and relevant skills have higher placement chances.

---

⚙️ Installation

Clone the repository

git clone https://github.com/XC0ID/Student-Placement-Prediction.git

Move to project folder

cd Student-Placement-Prediction

Install dependencies

pip install -r requirements.txt

Run the notebook

jupyter notebook

---

🧪 Example Prediction Workflow

Student Academic Data
        │
        ▼
Machine Learning Model
        │
        ▼
Prediction
        │
        ▼
Placed / Not Placed

---

🔮 Future Improvements

Possible enhancements:

• Hyperparameter tuning
• Feature importance analysis
• Deep learning models
• Web deployment using Flask or Streamlit
• Real-time placement prediction system

---

📚 Technologies Used

• Python
• Pandas
• NumPy
• Seaborn
• Matplotlib
• Scikit-learn
• Jupyter Notebook

---

👨‍💻 Author

Maulik Gajera

---

📜 License

This project is licensed under the MIT License.

---

🚀 Final Note

Machine Learning can transform education analytics by identifying patterns in academic data and helping institutions make smarter decisions for student success.

---