Project: Cook County Housing Analysis and Prediction

Part 1: Exploring Cook County Housing

File (Google Drive):

PDF version:

Objective:
Explored housing data from Cook County, Illinois, to understand patterns in housing prices and prepare for predictive modeling.

Key Activities and Findings:

• Exploratory Data Analysis (EDA): Visualized data distributions, identified outliers, and examined correlations between housing features and sale prices.

• Feature Engineering: Created and transformed features such as log-transformed sale prices, neighborhood indicators, and property details extracted from descriptions.

• Insights: Highlighted disparities in housing prices across neighborhoods and identified critical predictors like building size and property age.

Technologies Used:
Python (pandas, numpy), Visualization (Matplotlib, Seaborn)

Skills Demonstrated:

• Data cleaning and preprocessing

• Statistical analysis and visualization

• Transforming raw data into actionable features

Part 2: Predicting Housing Prices in Cook County

File (Google Drive):

PDF Version:

Objective:
Developed a linear regression model to predict property sale prices and analyzed its fairness and accuracy in the context of housing equity.

Key Activities and Results:

• Model Development: Built and evaluated regression models using engineered features such as building size, bedrooms, and neighborhood indicators.

• Ethical Analysis: Explored the implications of property assessments on marginalized communities, addressing potential biases in the model.

• Performance: Achieved a root mean squared error (RMSE) below key thresholds, ensuring robust predictions while balancing accuracy and fairness.

Technologies Used:

• Python (pandas, numpy, scikit-learn)

• Linear regression modeling and error analysis

Skills Demonstrated:

• Advanced feature engineering

• Model evaluation and error analysis

• Incorporating social context and fairness into predictive modeling