The **Data Science Club (DSC)** is launching a *Bi-Weekly Kaggle Challenge Series* to encourage students and data enthusiasts to build practical machine learning skills through hands-on competitions. Each challenge in this series is designed to simulate a real-world data science problem — from messy data to meaningful predictions.

This first competition introduces participants to one of the most important applications of data science: predicting real-world values from imperfect data. Using New York City’s real estate sales records, participants will experience how raw datasets collected in the real world often contain missing values, inconsistencies, and noise — and how these issues must be handled before any reliable model can be built.

Through this contest, participants will practice the complete data science workflow: data cleaning, feature engineering, exploratory analysis, and machine learning. The goal is not just to rank on the leaderboard, but to learn how to turn real-world data into useful insights — a skill that applies across every domain of data science.

This competition marks the beginning of DSC’s bi-weekly challenge series, where each new problem will introduce more advanced concepts, larger datasets, and deeper modeling techniques.

Regression Task: Predict SALE PRICE

   This is a normalized metric representing the property's valuation potential relative to its size and location.

   * Target: A continuous value prediction form data.
   * Objective: Identify which properties are undervalued or have high appreciation upside.