Data Analytics in Real Estate: How Zillow.Com Uses Social Media Information

Barbara A. Manko^*
*Correspondence: Barbara A. Manko, Department of Business Management, The Pennsylvania State University, University Park, PA 16802, USA, Email:

Keywords

Data analytics • Real estate • Data visualization • Smart phone • Big data frameworks • Property management

Introduction

Zillow.com and similar real estate websites are undeniably helpful in providing home buyers a one-stop shop to browse all the listings in their area, filtered by location, price, number of bedrooms and bathrooms, HOA fees, square footage, and more. It also allows communication with local agents and the ability to schedule walk-through appointments, all from the site or app. In addition, Zillow has a large social media presence with several unaffiliated Instagram accounts run by Samir Mezrahi, including Zillow Gone Wild, Zillow Gone Mild, and Zillow Gone Wild Celebrity Homes that highlights the best (or the best of the worst) listings available. On February 6, 2021, Dan Levy and the cast of Saturday Night Live parodied the idea of people browsing the listings and lusting over the available houses. The real estate market has become a source of entertainment, and this social media presence is beneficial to agents at all levels and has become part of the larger online culture. Indeed, with “a significant portion of users are susceptible to develop addictive behaviours related to Facebook use” (as well as similar social media sites) the addictive behaviours spread across app function to blur the lines between information and entertainment, especially when it comes to real estate listings [1]. In this article, the application of big data analytics from social media and websites and data visualization online as pertaining to real estate will be discussed.

Literature Review

Advancing technology affects homebuyers

Available houses for sale often have a plastic stand in the front yard with the sales sheet for any interested lookers who happen to pass by, but there are much more effective ways to market that will reach a wider audience. In fact, technology has advanced to the point where potential buyers can do a 3D virtual walk through of a property without leaving their couch, even if it is located 2,000 miles away. Although these systems provide users “convenient access to available real estates,” and allow users to “explore the properties by themselves,” “they still have some drawbacks," who are working on “multidimensional visualization methods” to help “less informed users…learn about the local real estate market step by step” [2]. By including intuitive and visual designs, data analytics can be built into a website to help home buyers who may not even realize how it works to aid them in their search. An effective analytics system “integrate state-of-the- art interactive visualizations to enable end users to…gain insight into the real estate market” [3]. This is part of the user friendly design of Zillow, to organize listings in a way that appeals to the searcher.

This doesn’t only help the homebuyers, but also the company offering listings. 3D technology levels the playing field for SMBs in real estate “the same way Amazon has created a level playing field for all sellers,” suggests [4]. “3D visualizations give them the power to avail the luxury of easily showcasing even the most complex of projects to clients worldwide.” The importance of appearance cannot be underestimated. In fact, when calculating market value, sites like Zillow Trulia and Refin have proprietary formulas to determine market value, which sometimes turns out to be “highly inaccurate” [5]. He found that “in addition to home characteristics including size, offered price and number of bedrooms… one of the key factors that affects the value of a house is its interior and exterior appearance, which is not considered in calculating automatic value estimates,” especially when it comes to “luxury” listings and including this information outperforms Zillow’s automatic estimate formula [5].

Just as real estate agents have often showcased a home in the past with pictures taken from flattering angles or artfully cropped, which end up being inaccurate at best to highly misleading when compared to reality, data visualization can be skewed in presentation. He has an insightful observation on the use of data visualization:

The goal of data visualization is to convey a story to the viewer [6]. This story could be in the form of general trends about the data or an insight. Creating effective data visualizations is similar to being good at storytelling: It involves conveying relevant and interesting information at the right level of detail. This makes the data visualization task more of an art and less of an exact science. Along with the core statistical insights that we intend to present, aesthetics of presentation are equally important. This is not to say that we can hide the lacunae of our analysis by clever presentation tricks. Just like clear writing, clear and effective presentation should make our data analysis transparent, so that the viewer can fully understand and appreciate the complete picture.

Discussion

Big data analytics in real estate

Data analytics can be complex in any scenario, with a large volume of information that is often rapidly changing. “The analysis of the real estate market is very challenging as the data are high dimensional and have complex spatial and temporal patterns” [3]. However, even though challenging, the use of the available data is worth the effort. “Big data can tackle the ever-present issues of customer regrets related to poor quality of information or lack of information in smart real estate to increase the customer satisfaction using an intermediate organization that can process and keep a check on the data being provided to the customers by the sellers and real estate managers” [7]. “Perceived attractiveness” can be used as a “quantitative measure” to predict the best ways to present a home for sale [8]. “Major characteristics of big data can be summarized using the seven vs., which include variety, volume, variability, value, visualization, veracity, and velocity” [7]. By focusing on the wants of customers, listings can be targeted to appropriate parties.

There are many examples of how big data analytics can be used to provide information about target audience, market trends, and effective growth or sales strategies. “Internet marketing research contains a large amount of objective user-generated and system-recorded data when users/ consumers interact with the target websites” [9]. Looking at Facebook as an example, the advertisement manager allows the performance of paid ads to be tracked, “including aggregated demographics of Facebook users who clicked on the advertisement, their likes and interests according to their Facebook profiles, and more” [10]. This data can be used on a macro and micro level. See for a visualization of the vast amount of data that can be generated in just one minute across various websites (Figure 1). Regarding the big picture, combining online Facebook user information with a comparison to a country’s overall development and gender gaps can help identify internet and mobile phone gender gaps [11]. When it comes to the micro level, it can provide analytics on the effectiveness of the website itself: “Click analytics is a powerful technique that displays what and where users are clicking on a webpage…to easily identify areas of high and low usage on a page without having to decipher website use data sets” [12]. In real estate, as in many industries, the budget for offline marketing is still higher than online, as people do still use traditional methods to search for available properties, but increasing digital services can have a “powerful impact” that they describe as “radical” when it comes to business performance [13].

Analyzing the data can be beneficial when evaluating the best time to invest in real estate, especially when the decision makers are often family members or a group of people with different opinions. The “investment environment” includes factors such as available resources and funds, estate development and social needs and market capacity to maximize profits [14]. “Understanding price dynamics in the real estate market constitute an important aspect of diagnosing city growth. Introducing effective policies to stabilize price trends and support a sustainable housing market is reinforced by having representative price indicators that do not neglect spatial heterogeneity and autocorrelation effects” [15]. Besides facilitating users’ ability to find their dream property, big data also leads to profits for the company. But, by thinking outside the box, it can affect health and safety as well: “Big data generated from the smart real estate in the form of occupant data, facilities management, and building integration and maintenance can be shared with the disaster risk management and emergency response teams to help prevent, prepare, respond to, or recover from the disasters” [7].

Conclusion

The user-friendly nature of the Zillow.com website has had people flocking to it in droves-whether they are serious about buying in the near future or not. By offering a website and app design that mimics the type of social medial posts people like to view, they have increased their market appeal. As Zillow and similar sites use data visualization and data analytics to interpret customer needs and then reflect their desires back to them, they increase the turnaround speed of real estate sales and influence the market. Studying the affect and applying it in the new ways can change not only real estate, but the way people interact as a culture.

Acknowledgement

The author praises leaders at Gannon University in Erie, Pennsylvania, for opening an MBA Analytics program and inviting students from around the world to study.

Dr. Karinna Vernaza is Dean of the College of Engineering and Business and a professor of Mechanical Engineering at Gannon.

Dr. Amy L. Doolan is Associate Dean and Director of the Dahlkemper School of Business.

Dr. Celene M. Kalivoda, CPM, CPSM is Director of the MBA Program, Chair of Operational Systems in the Marketing Program, and an assistant professor of Supply Chain Management.

Dr. Eric A. Brownlee is Chair of Market Focused System in Business Administration and an associate professor of Graduate Business Studies and of Sport Management and Marketing.

Thanks to the work of these leaders, Gannon’s MBA Analytics program is equipping students for success. "Analytics is a way of thinking".

Also, the author would like to acknowledge a friend from the faculty at Clarion University: Dr. Kreag Danvers, Professor of Accountancy–College of Business Administration & Information Science

In addition, the author thanks the chief editors of the International Journal of Sensor Networks and Data Communications for giving her the opportunity to share knowledge and work experience with people around the world. Finally, the author thanks the anonymous reviewers for their insightful suggestions on the manuscript. Although the work on this paper was self-funded, the author wishes to acknowledge the institutions that have employed her and the colleagues she has met through them.

Conflict of Interest

The author declares that there are no conflicts of interest regarding the publication of this article.

References

1. Shettar, Manoj, Ravichandra Karkal, Anil Kakunje and Rohan Dilip Mendonsa, et al. “Facebook Addiction and Loneliness in the Post-Graduate Students of a University in Southern India.” Int J Soc Psychiatry 63 (2017): 325-329.
2. Li, Mingzhao, Zhifeng Bao, Timos Sellis and ShiYan, et al. “HomeSeeker: A Visual Analytics System of Real Estate Data.” J Vis Lang Comput 45 (2018): 1-16.
3. Sun, Guo Dao, Rong Hua Liang, Fu Li Wu and Hua Min Qu. “A Web-Based Visual Analytics System for Real Estate Data.” Sci China Inf Sci 56 (2013): 154-166.
4. Rakheja, Jagrati. “How 3D Visualization Technology Transforming Real Estate SMBs?” PC Quest, 17 (2018): 1-10.
5. Poursaeed, Omid, Tomas Matera and Serge Belongie. “Vision-Based Real Estate Price Estimation.” Mach Vis Appl 29 (2018): 667-676.
6. Pathak, Manas A. “Data Visualization.” Beginning Data Sci R 1 (2014): 31-60.
7. Munawar, Hafiz Suliman, Siddra Qayyum, Fahim Ullah and Samad Sepasgozar. “Big Data and Its Applications in Smart Real Estate and the Disaster Management Life Cycle: A Systematic Analysis.” Big Data Cognitive Comput 4 (2020): 4.
8. Kostic, Zona and Aleksandar Jevremovic. “What Image Features Boost Housing Market Predictions?” IEEE Trans Multimedi 22 (2020): 1904-1916.
9. Xun, Jiyao. “Revisiting the Two-Stage Choice Model: An Empirical Study of Consumer Choice on Brand Website Visits.” Behav Inf Technol 33 (2014): 1192-1207.
10. Chan, Christopher. “Using Online Advertising to Increase the Impact of a Library Facebook Page.” Lib Manag 32 (2011): 361-370.
11. Fatehkia, Masoomali, Ridhi Kashyap and Ingmar Weber. “Using Facebook Ad Data to Track the Global Digital Gender Gap.” World Dev 107 (2018): 189-209.
12. Farney, Tabatha A. “Click Analytics: Visualizing Website Use Data.” Inf Technol Lib 30 (2011): 141. 
13. Jarvinen, Joel and Heikki Karjaluoto. “The Use of Web Analytics for Digital Marketing Performance Measurement.” Ind Mark Manag 50(2015): 117-127.
14. Wu, Wenshuai and Gang Kou. “A Group Consensus Model for Evaluating Real Estate Investment Alternatives.” Financial Innov 2 (2016): 1-10.
15. Agarwal, Sumit, Ying Fan, Daniel P. McMillen and Tien Foo Sing. “Tracking the Pulse of a City-3D Real Estate Price Heat Maps.” J Reg Sci 61 (2021): 543-569.