Welcome to my project focused on analyzing income patterns and exploring the various factors influencing household livelihood in the United States. This project was done as a group project for the course BUDT704: Data Processing and Analysis in Python. As a group of passionate graduate students in MSIS of the University of Maryland College Park, we conducted this project to gain insights into income disparities and shed light on areas that require assistance. Through data analytics, visualizations, and predictive modeling, our aim is to contribute to a better understanding of the factors that impact income and identify opportunities for improvement.
In this project, we delve into the data from the US Census to investigate the relationship between income and various socio-economic factors. By exploring questions related to education, employment, and other characteristics, we aim to uncover insights that can help address income disparities in different states. Additionally, we develop a predictive model to estimate income based on these factors, providing valuable insights for organizations and policymakers.
- What is the median household income in the United States, and how does it vary across different states? How is the distribution of employment types related to income?
- How do the distribution of education levels and employment within a state impact income levels?
- Can we build a predictive model to understand the impact of each factor on income and estimate the income for a given state based on these factors?
- Based on the income predicted by the model, what opportunities exist for states to improve their median household income, and what factors are crucial in achieving this improvement?
Part 1: Understanding variations in median income across states provides valuable insights into economic disparities and successful employment structures. By identifying states that fall below the national average, we can focus our efforts on exploring potential improvement opportunities.
Part 2: Exploring the relationship between education levels and income helps us determine if higher education leads to better job prospects and increased income. By comparing states with the highest and lowest income levels, we aim to validate the impact of education on income.
Part 3: Developing a robust model enables us to make accurate income predictions, facilitating the identification of states with room for improvement.
Part 4: Once we identify states with potential for change, we must prioritize factors contributing to income improvement. Our analysis will guide organizations in determining where to focus their efforts first.
The data used in this project was obtained from the US Census data website (https://data.census.gov/) for the year 2020. We collected information from the following tables:
DP03: Economic characteristics
DP05: Demographic and housing estimates
S1501: Educational attainment
S2506: Financial characteristics for housing units
To analyze the data, we leveraged our knowledge and skills to consolidate and preprocess the data. By combining relevant columns from these tables using the zip code as the primary key, we created a comprehensive dataset for my analysis.
Finally, I would like to extend my gratitude to exceptional team members Satvik Narang, Shweta Salelkar, and Anushka Ranjan for their invaluable contributions, collaborative spirit, and dedication throughout this project. I would also like to express my heartfelt appreciation to our professor Dr. John Bono for his unwavering support and guidance.