# Relationship Status Prediction Challenge of NITJ Students
**GDGC NIT Jalandhar – AI/ML Inductions Kaggle Competition**

---

## Problem Statement  
In this challenge, your task is to **predict the relationship probability (on a 0–100 scale)** for students at NIT Jalandhar using a variety of personal, academic, and social features.

This is a **regression problem**, where the target is a continuous value representing the likelihood of a student being in a relationship. Your model should learn meaningful patterns from the training data to make accurate predictions on unseen test samples.

---

## What Makes This Challenge Interesting?

- **Real-world inspired**: The dataset reflects diverse aspects of student life, making it a fun and relatable modeling task.
- **Encoded features**: All features are anonymized and encoded, requiring smart feature engineering and interpretation.
- **Distribution shift**: The test set has a different target distribution than the training set, so naive validation may mislead you.
- **Noise and relevance**: Not all features are useful—some are noisy or irrelevant. Feature selection will be key.

---

## Goal  
Build a robust regression model that generalizes well to the test set and achieves a high score on the custom evaluation metric.

---

## Ready to dive in?  
Explore the data, decode the features, and start building your predictive pipeline. May the best model win!