How I Use Data Analytics in Real Estate Investing—Or How I Failed My Way to Success

In This Article

In 2004, I was living in NYC when I decided to start a new career. To identify potential business opportunities, I thought about some of the more frustrating experiences I’d had. I quickly narrowed the list to buying investment properties.

The problem was that all real estate agents could do was send me MLS data sheets for the properties I selected; no analytics, processes, or services. I had to do everything myself. This was time-consuming, and I made frustrating mistakes that cost me time and money to correct later. 

So, there was a business opportunity. Now, I need to know where to create this business (not New York or New Jersey).

How I Did My Analysis

I started researching how retail store chains select locations for new stores. Based on my research, I determined the sequence of events necessary for success, as shown in the chart.

My first decision was location. Based on my research, I selected Las Vegas.

The next step was to determine the right tenant pool segment to target. This step is crucial because the only way to have a reliable income is if reliable tenants continuously occupy the property. A reliable tenant stays for many years, always pays the rent on schedule, and takes good care of the property.

Based on my experience with rental properties and what I learned from others, reliable tenants are the exception, not the norm. Because my clients and I plan to hold these properties for many years, we will need multiple reliable tenants throughout the hold time. The best way to increase the chances of always having a reliable tenant is to purchase properties that attract people from a segment with a high concentration of reliable people.

Therefore, my task was to find a tenant segment with a high concentration of reliable tenants.

As an engineer, I used the standard approach of analyzing data. I tried various (paid and free) data sets and wrote a lot of software, but (I would be embarrassed to tell you how long I persisted) I finally decided that classic data analysis would not work. The fundamental problem is that humans do not behave algorithmically. So, I ditched this approach.

Next, I decided to mine historical rental data to understand past tenant behaviors. I downloaded about 10 years of MLS rental history data and started over. I tried many things (that failed), and then I plotted monthly rent versus length of stay. 

The result was similar to the chart, showing a strong correlation between how long a tenant stays in the property and the amount of rent. This was the starting point I had been searching for.

I investigated the segment of tenants who stayed over five years, converting the low and upper rent range of properties they occupied to approximate gross monthly income using monthly rent/30% = gross monthly wage.

I next interviewed property managers and cruised job boards to determine probable jobs based on gross monthly income. By doing this, I concluded that people earning below a certain wage tended to have lower-skilled jobs, which made them vulnerable to layoffs during economic downturns. Therefore, I raised the lower-income threshold above this wage.

I next looked at the upper-end income range and determined that jobs above a certain wage were primarily administrative. These workers would also be laid off during economic downturns. So, I lowered the upper-income threshold below this wage level.

The result was a narrow wage/rent range that I believed to have secure jobs due to the nature of their work, as shown in the chart.

Each tenant segment has specific housing requirements and is unlikely to rent a property if it does not meet all their requirements. So if you buy a property that matches the housing requirements of a specific tenant segment, most of the applicants will be from that segment.

Creating a Property Profile

To determine the characteristics of properties that would attract my target tenant segment, I used data analytics to determine what and where they rent today. From this, I created what I refer to as a property profile. 

A property profile is a physical description of the properties that this segment is currently renting. It has at least four elements:

• Location: The locations where significant percentages of the target segment are renting today.
• Property type: What type of properties are they renting today? Condo, high-rise, multifamily, single-family?
• Rent range: What the segment is willing and able to pay.
• Configuration: Two bedrooms, three-car garage, large backyard, single-story, two stories?

I ran correlations between properties identified by the property profile and actual historical rental data and found a high correlation between the two. After so long, I thought I had what I needed.

And then reality came crashing down.

The issue was that numerous new listings entered the market daily, and the most desirable properties often went under contract within two to three days. This left us only 24 to 36 hours after a property was listed to identify it as a potential option, evaluate it, gather analytical information, and submit an offer.

Doing this process manually for hundreds of properties each day was impossible. So, once again, I turned to data analytics.

Our Data Mining Engine

I’ve worked on data mining engines for investment property selection since 2007. All the algorithms I tried were similar to what Rentometer, Zillow, and Opendoor were using, which was not nearly good enough to make purchase decisions. 

Finally, around 2015, I discovered a very different methodology to find good properties. I am still enhancing that software to this day.

Our data mining engine architecture is illustrated here.

After years of improvements, the engine can now find the small number of potential investment properties from among thousands in less than five minutes.

However, data analytics can only go so far because software only deals with data, and we are dealing with humans.

I next put together a team and processes that took the output of the data mining engine and selected properties that matched individual clients’ requirements. These properties are then rigorously evaluated by a team of experts, as illustrated in the chart.

Only if a property matches the client’s requirements and passes evaluation by multiple team members do we send the client a property report containing the analytical information they need to make an informed decision. Due to our software, processes, and team members, we can evaluate numerous properties in a single day and present our clients with actionable information on properties that match their individual profiles within that same day.

Our clients feel our data analytics and processes are effective.

Final Thoughts

Data analytics and processes are the cornerstone of our business. Without data analytics, we could not find the properties needed to meet our client’s specific financial goals. Also, we could not evaluate properties fast enough to make offers before they were gone.

Note By BiggerPockets: These are opinions written by the author and do not necessarily represent the opinions of BiggerPockets.