About Me Introduction Data Sources Data Visualization Exploratory Data Analysis ARMA/ARIMA/SARIMA Models ARIMAX/SARIMAX Models Financial Time Series Models Deep Learning for TS Conclusions

Conclusion

The homeownership rate is the percentage of households in a particular area, such as a city or country, that own their home rather than rent. It is calculated by dividing the number of owner-occupied households by the total number of households in the area and multiplying by 100. The homeownership rate is an essential indicator of the health of the housing market and the broader economy. It is also a critical factor in determining individual households' wealth and financial stability, as homeownership can provide long-term investment and a source of financial security.

Overall, the homeownership rate in the US has fluctuated over time due to various factors, including economic conditions, government policies, and demographic changes. Notably, in the last couple of years, the homeownership rate in the United States has increased slightly in the previous couple of years due to a combination of factors, including strong economic growth, low mortgage rates, generational changes, and government policies. The pandemic has led to changes in the housing market, including increased demand for larger homes and suburban properties, which may have contributed to the rise in homeownership rates.

This project uses data of different economic indicators that are available on the Federal Reserve Bank of St. This includes, The Homeownership rate in the United States, Median Sales Price of Houses Sold for the United State, Personal Saving Rate, Unemployment Rate, and Federal Funds Effective Rate.

Findings from the ARIMAX model suggest that homeownership rates will remain steady despite the increase in the interest rate and ongoing uncertainty in the overall economy. Of the different models used in the study, deep learning models such as RNN, LSTM, and GRU were able to predict the data accurately. With the deep learning models, there were issues of overfitting that we could resolve using "regularizers to RNN" methods.

In the future, I would like to improve the study by accounting for additional data specific to geographical locations. In addition, I would also like to account for the latest policy proposed by the Biden Administration for homebuyers with lower credit scores.