Need For Study

The real estate market can be described briefly as the business sector that deals with housing. It could be residential, commercial, or industrial (Benefield & Hardin, 2013). Among these, residential housing is well-known to people, especially in the US.

In this sector, housing attributes such as time on the market, location, supply and demand, and economic growth or decline among others are the key drivers for pricing (Grybauskas et al., 2021).

The outbreak of the Covid pandemic had a huge effect on many industries. The real estate market is one of these many industries that is purported to have been impacted, and some research has been carried out to shed light on the extent of the impact. Grybauskas et al. and Benfield et al. studied the effect of the Covid-19 pandemic on residential real estate and found that the time-on-the-market during the pandemic had an impact on price revision (Benefield & Hardin, 2013; Grybauskas et al., 2021). Balemi et al. and Tanrıvermis also had similar findings (Balemi et al., 2021; Tanrıvermiş, 2020).

With the steady decline in Covid-19 cases across the globe, most countries are returning to in-person activities including workers returning to the office. Nonetheless, it has been shown during the pandemic working remotely in many business areas can be as productive as in-person if that is the only option available. This has made working-from-home a strong feature in many business areas. Recent studies have shown a greater chance of current remote work becoming permanent (Barrero et al., 2021).

According to a recent report, finance, management, professional services, and information sectors come up top when it comes to the potential to work remotely (Lund et al., 2020). Wieland and Mondragon investigated housing demand and remote work and noted that remote work contributed tremendously to the house price increase since 2019 (Wieland & Mondragon, 2022). They concluded that the evolution of working remotely will continue to impact the prices of houses post-covid.

Of the many attributes that impact residential real estate pricing, location is the most likely to impact price revision with the advent of remote working. Historically, the pricing of apartments in the business district of cities like New York City is notably high. Since proximity to work may no longer be the primary factor when considering housing, it is possible that people will opt for suburban residential housing.

There is a need to investigate housing trends, especially in areas that are dominated by employees in industries who can potentially work from home. Findings from such a study can inform stakeholders in the housing sector to direct their resources into, for example, the residential real estate market with a focus on suburban areas rather than metro areas.

Research Problem

The research problem for this study is the repercussions of the Covid-19 pandemic specifically remote working are differentially impacting the trend of housing prices in suburban and urban areas post-covid. The proposed research is to study how working from home is influencing the shift in residential housing demand from the financial districts of major US cities to suburban areas after the pandemic.

Research Question

Descriptive question: What is the pricing trend of residential real estate post-covid pandemic?

Inferential question: What is the relationship between working from home post-covid and the prices/sales of houses?

Predictive question: How often will people continue to work from home post-Covid-19 pandemic and its impact on housing prices/sales?

Hypothesis

Descriptive Question Hypothesis:
Null hypothesis: The pricing trend of housing post-covid did not change in urban and suburban areas.
Alternative hypothesis: The pricing trend of housing post-covid did change in urban and suburban areas.

Inferential Question Hypothesis:
Null hypothesis: There is no relationship between working from home post-covid and the prices/sales of housing.
Alternative hypothesis: There is a relationship between working from home post-covid and the prices/sales of housing.

Predictive Question Hypothesis:
Null hypothesis: More people will not continue to work from home resulting in less impact on housing prices/sales.
Alternative hypothesis: More people will continue to work from home resulting in a greater impact on housing prices/sales.

Research Plan

The data acquisition method to be used for this study will be via web scrapping algorithms on Zillow.com. For data cleaning, empty cells will be deleted, and the data will be transformed, if needed, to reduce skewness (Lun & Khattree, 2021). The dependent variable is price/sales, and the independent variables are location, type of housing, size, amenities, and buyer’s employment history.

A stratified cross-validation sampling process would be used for this study. The acquired dataset will be split into complementary strata/subsets. For each stratum, analysis and training of a fraction of the strata will be performed and used for the remaining fraction of that stratum to test. The number of subsets depicts the number of different times the model chosen will be trained.

Although several pieces of training will be conducted, slightly different versions of the data will be used to prevent overfitting or selection bias. Unsupervised learning methods will be used for data exploration, and the supervised learning method will be used for making predictions. Descriptive statistical analysis will also be carried out to understand the dataset better.

Author: Adwoa Osei-Yeboah

---

References

Balemi, N., Füss, R., & Weigand, A. (2021). COVID-19’s impact on real estate markets: Review and outlook. Financial Markets and Portfolio Management, 35(4), 495-513. https://doi.org/10.1007/s11408-021-00384-6

Barrero, J. M., Bloom, N., Davis, S. J., & Meyer, B. H. (2021). COVID-19 is a persistent reallocation shock. AEA Papers and Proceedings, 111, 287-91. https://doi.org/10.1257/pandp.20211110

Benefield, J. D., & Hardin, W. G. (2013). Does time-on-market measurement matter? The Journal of Real Estate Finance and Economics, 50(1), 52-73. https://doi.org/10.1007/s11146-013-9450-z

Grybauskas, A., Pilinkienė, V., & Stundžienė, A. (2021). Predictive analytics using big data for the real estate market during the COVID-19 pandemic. Journal of Big Data, 8(1), 105. https://doi.org/10.1186/s40537-021-00476-0

Lun, Z., & Khattree, R. (2021). Imputation for skewed data: Multivariate lomax case. Sankhya B: The Indian Journal of Statistics, 83(1), 86-113. https://doi.org/10.1007/s13571-021-00251-

Lund, S., Manyika, J., & Smit, S. (2020, Nov. 23,). What’s next for remote work: An analysis of 2,000 tasks, 800 jobs, and nine countries., 1-13. https://www.mckinsey.com/featured-insights/future-of-work/whats-next-for-remote-work-an-analysis-of-2000-tasks-800-jobs-and-nine-countries

Tanrıvermiş, H. (2020). Possible impacts of COVID-19 outbreak on real estate sector and possible changes to adopt: A situation analysis and general assessment on turkish perspective. Journal of Urban Management, 9(3), 263-269. https://doi.org/https://doi.org/10.1016/j.jum.2020.08.005

Wieland, J., & Mondragon, J. A. (2022). Housing demand and remote work. (). Cambridge: National Bureau of Economic Research. https://doi.org/10.3386/w30041 http://www.nber.org/papers/w30041