Analyzing Real Estate Trends

A project analyzing housing market trends and pricing insights for buyers and sellers, using public datasets and building dashboards for clear visualization.

Skills

Python

pandas

numpy

matplotlib

Excel

The Problem

Real estate prices often feel unpredictable, leaving buyers unsure if a property is fairly priced and sellers uncertain how their home compares to the market. To address this, I analyzed King County housing sales (2014–2015) using Python and Excel to explore pricing trends, correlations, and location-based differences.

The project focuses on descriptive analysis rather than predictive modeling, nationwide datasets, or API integrations (e.g., Zillow/Redfin), which are left as future improvements. Constraints include relying on a single regional dataset with limited property features, excluding factors like HOA fees, school ratings, or crime statistics.

The Goal

The goal of this project was to uncover meaningful insights into housing market dynamics and present them in a clear, accessible format. Specifically, the project aimed to analyze pricing trends, identify key drivers of home values, and make comparisons across different regions and time periods.

By combining Python for data cleaning and statistical exploration with Excel dashboards for interactive visualization, the project sought to bridge technical depth with usability. The ultimate objective was to create a tool that could help buyers and sellers better understand market conditions while also showcasing practical data analysis and dashboard development skills.

Approach

To achieve the project goal, I combined data science methods with accessible dashboard tools to balance technical depth and usability. There were 3 steps to this project:

1. Data Preparation
   • Collected housing sales data from Kaggle.
   • Cleaned and standardized the dataset to handle missing values, outliers, and inconsistent formats.
   • Engineered new features such as price per square foot for more meaningful comparisons.
2. Exploratory Data Analysis (EDA)
   • Performed descriptive statistics to understand central tendencies and distributions.
   • Used correlation analysis and heat maps to test relationships between price and property features.
   • Examined location-based groupings (by zip code) and time-series trends to uncover regional and temporal patterns.
3. Visualization & Dashboard Development
   • Built static and exploratory charts in Python to validate hypotheses and highlight key findings.
   • Designed an interactive Excel dashboard combining PivotTables and PivotCharts, enabling filters by region, property size, and month.
   • Structured the dashboard for clarity so users could move from high-level insights to detailed comparisons.

Process/Results Images