Category Archives: Technology

Time Series Home Value Index

Time-Series Home Value Index Tutorial using auto.arima()

Using 3 Years of Monthly Sales Data (2014-2016) for Zip Code 92508
in Riverside, CA, this tutorial demonstrates how to fit an optimal ARIMA
in R using auto.arima()

#Import Libraries

Generate Unadjusted Median Sale Price Index

#View Data
#Format Date
df.priceMedian92508$date <- as.Date.character(df.priceMedian92508$dateSaleMoYr, "%m/%d/%Y")
#Convert to tbl class and view first 12 months
tbl_df(df.priceMedian92508) %>%
# A tibble: 38 × 6
   dateSaleMoYr dateSaleMonth dateSaleYear idZip priceMedian       date
          <chr>         <chr>        <chr> <chr>       <dbl>     <date>
1    01/01/2014            01         2014 92508      351500 2014-01-01
2    02/01/2014            02         2014 92508      405000 2014-02-01
3    03/01/2014            03         2014 92508      395000 2014-03-01
4    04/01/2014            04         2014 92508      404000 2014-04-01
5    05/01/2014            05         2014 92508      402500 2014-05-01
6    06/01/2014            06         2014 92508      396500 2014-06-01
7    07/01/2014            07         2014 92508      376750 2014-07-01
8    08/01/2014            08         2014 92508      375000 2014-08-01
9    09/01/2014            09         2014 92508      387000 2014-09-01
10   10/01/2014            10         2014 92508      410000 2014-10-01
11   11/01/2014            11         2014 92508      399000 2014-11-01
12   12/01/2014            12         2014 92508      380000 2014-12-01
# ... with 26 more rows

#View for Sale Year 2016
df.priceMedian92508 %>%
  filter(dateSaleYear == "2016") %>%

   dateSaleMoYr dateSaleMonth dateSaleYear idZip priceMedian       date
          <chr>         <chr>        <chr> <chr>       <dbl>     <date>
1    01/01/2016            01         2016 92508      375000 2016-01-01
2    02/01/2016            02         2016 92508      425000 2016-02-01
3    03/01/2016            03         2016 92508      407500 2016-03-01
4    04/01/2016            04         2016 92508      430000 2016-04-01
5    05/01/2016            05         2016 92508      444250 2016-05-01
6    06/01/2016            06         2016 92508      444000 2016-06-01
7    07/01/2016            07         2016 92508      407500 2016-07-01
8    08/01/2016            08         2016 92508      418000 2016-08-01
9    09/01/2016            09         2016 92508      420000 2016-09-01
10   10/01/2016            10         2016 92508      446000 2016-10-01
11   11/01/2016            11         2016 92508      450000 2016-11-01
12   12/01/2016            12         2016 92508      435000 2016-12-01

Plot Line Chart

Unadjusted Median Sale Price


ggplot(df.priceMedian92508, aes(date, priceMedian)) +
geom_line() +
scale_x_date('date')  +
ylab("Median Sale Price") +


Include 3 Month Moving Average

df.priceMedian92508$price_ma3mo = ma(df.priceMedian92508$priceMedian, order=3) #3mo moving avg
ggplot() +
  geom_line(data = df.priceMedian92508, aes(x = date, y = priceMedian,   colour = "Median Price"))  +
  geom_line(data = df.priceMedian92508, aes(x = date, y = price_ma3mo,   colour = "3mo moving avg"))  +
  ylab('Median Sale Price')


Apply Seasonal Adjustment using Loess method.

price_ma = ts(na.omit(df.priceMedian92508$price_ma3mo), frequency=12) #Frequency = 12 for monthly data
decomp = stl(price_ma, s.window="periodic")
deseasonal_price <- seasadj(decomp)


Implement Augmented Dickey Fuller Test for Stationarity
HO (Null Hypothesis) is data is non-stationary. p=.228
Cannot reject H0 with 95% confidence (p=.05).

adf.test(deseasonal_price, alternative = "stationary")
	Augmented Dickey-Fuller Test

data:  deseasonal_price
Dickey-Fuller = -2.8851, Lag order = 3, p-value = 0.2288
alternative hypothesis: stationary


First-Order Difference to obtain stationarity, p=.0482
We can now reject H0 with 95% confidence.

Now let’s fit the ARIMA model using auto.arima()
We know we’ll need to include a first order difference in the ARIMA model – ARIMA(p,d,q) d=1 from the ADF test we just performed.

Now let’s see if auto.arima() confirms.

fit<-auto.arima(deseasonal_price, seasonal=FALSE)
tsdisplay(residuals(fit), lag.max=45, main='(0,1,0) Model Residuals')
#ARIMA(0,1,0) Random Walk

Time to Forecast

#Forecast h = horizon periods
fcast <- forecast(fit, h=3)

Real Estate’s Dawn of the Drone

Cameras aboard drones are set to bring a new set of eyes to the industry. Drones’ capabilities allow agents and property managers to obtain views not otherwise available to prospective buyers. Additionally, they would come in handy for inspecting roofs, pipes and overall property.  Anything outside private residential flights is still illegal unless you obtain exemption “Section 333” from the FAA.  However, change is on the horizon – It is indeed the Dawn of the Drone.

The FAA Modernization and Reform Act of 2012 tasked the FAA with implementing clear-cut regulations allowing for the commercial use of UAVs to be done no later than September 30, 2015 but we may not need to wait that long.

Rumours that the Federal Aviation Administration (FAA) may relax its restrictions on commercial drones that fly outside of the operator’s line of sight received the official stamp of credibility at the Association for Unmanned Vehicle Systems International’s annual trade show earlier this month. This past Friday in Washington, Doug Trudeau, Associate of Tierra Antigua Realty in Tucson, Arizona, appeared on a panel at a National Association of Realtors conference to explain how he obtained the first real estate exemption for drone use from the FAA.

When asked if a real estate agent could fly a drone as a hobbyist and then use photos from that flight later to help sell a house, he said yes.

“It’s a little nuanced, but I don’t think the FAA is going to get too concerned about that,” he said.

On April 17th, 2015 licensed private pilot and real estate industry professional Jeff Galindo, principle of Real Estate Strategies, LLC, received the special exemption “Section 333” from the FAA as well.  Jeff Galindo is the first real estate agent in the State of Nevada to be granted this exemption.

To date, the FAA has granted approximately 100 of these 333 exemptions to a variety of companies nationwide. This  underscoreshow hard it is to obtain this exemption for commercial purposes.

In granting the exemptions, the FAA considered the planned operating environments and required certain conditions and limitations to assure the safe operation of these Unmanned Aircraft Systems (UAS) in the National Airspace System. Several key regulations are enforced – operations require both a pilot and observer, the pilot must have proper certification, and the UAS must remain within line of sight at all times.

Galindo noted,

“This new generation of unmanned aerial vehicles reaffirms the age-old notion that a picture is worth a thousand words. In the case of video, it’s really more like a million words!”

Right now they’re getting far more use in residential than commercial, but commercial use is indeed rising as we see the further loosening of FAA restrictions.

4 Marketing Tips to Jump Start your Real Estate Career

1) Predictive Technology

Finding prospective clients in today’s market has become more competitive than ever and tech-savvy agents are finding a way to stay ahead of the game by predicting which homeowners are likely to sell. Buying data subscriptions and purchasing predictive leads from websites like My Listings Agent and Smartzip promise agents a scientifically proven way to find prospective clients by using big data and predictive analytics.  James Craig, CEO & co-founder of My Listings Agent, says they use big data to create a “Listing Score” for each home that shows how likely that owner is to sell.

Some real estate tech companies are using more traditional outlets of data to to generate leads.  Scanning obituaries for leads has long been a tactic of up-and-coming real-estate agents looking for an alternative way to generate business, and today, the practice is getting a 21st-century makeover.

Major life events such as marriage, divorce, and death frequently entail a home purchase or sale—and new businesses have found innovative ways to use these public records for real estate marketing.  Morry Eghbal, a co-founder of the website Successors Data (briefly known as, says the 1-year-old company, based in Rancho Cucamonga, Calif., already has 1,000 paid subscribers at $99 a month. Along with scanning obituary records, Successors Data searches the records of title companies for estates of deceased homeowners that are likely to enter the probate-court process.

How it Helps: Use predictive technology to generate high quality micro-targeted leads.  Big data and predictive analytics is still relatively new to real estate which ensures you a competitive advantage over other agents for the foreseeable future.

2) Go Out and Walk the Neighborhood!

I can’t stress this point enough when I talk to new agents.  While technology is a necessary and growing component of your real estate business it is not the ONLY component.  The traditional approach to find prospective clients, that being interpersonal contact, still remains one of the most effective ways to generate new business as a real estate agent.

So go out and walk!  Knock on doors, leave flyers, etc.  As mentioned above, predictive technology now allows agents to identify which homeowners in the neighborhood are most likely to sell, so instead of sending prospective clients a postcard in the mail go out and visit them instead!

How It Helps: With the advent of technology, interacting with prospective clients face to face has gone by the wayside.  Agents report walking neighborhoods and visiting prospective clients in person as the most effective way to generate new business.

2) Be Mobile and Respond ASAP

Mobile is now in the majority. Sixty-six percent of emails are opened on a phone or tablet. Facebook has more than 650 million daily active users on mobile devices. And mobile traffic to websites now accounts for almost 30 percent of visits. Simply put, mobile devices continue to grow in popularity while computer use remains on the decline.

Competent use of mobile technology is also important in terms of how responsive you can be as a real estate agent. With mobile devices you can respond to the inquiries of prospective clients almost instantaneously, – so respond ASAP, before another agent does first!

How It Helps: Being mobile-friendly provides a positive first impression to prospective clients and will allow you to be more responsive in your real estate business.

3) Automate your Marketing

Sending an online newsletter or sharing content across a variety of social networks should no longer be a manual process for real estate agents.  Marketing services such as Corefact and Sharper Agent will allow you to automate both your direct mail and online marketing campaigns, go ahead and check em out!

How It Helps: Automating your marketing helps free up your time and will allow you to be more efficient in your real estate business.

4) Avoid Zillow/Trulia

Paying for leads from these websites is expensive and simply doesn’t work.  On average, agents spend $320 per month on leads from Zillow, and it’s estimated that leads from these websites convert to new business only one to four percent of the time. Not the best use of your marketing dollars.

Zillow and Trulia provide a service that many casual home shoppers want: a consolidated list of available homes for sale in a centralized location. However, most agents (with good reason) don’t like the idea of their listings being submitted to these services only to then have to pay to be featured as the listing agent.  And we don’t blame them.

How It Helps: Spending your money on mass online marketing is expensive, over-saturated, and ineffective.  Instead, use predictive technology to obtain leads at a fraction of the cost and start spending your marketing dollars smarter.

Real estate gets more tech.

For those of us in the tech world with a background in real estate, the impending tech opportunities in real estate may appear obvious. Real estate is a sector of the economy that’s done quite well despite it’s glacial movement towards tech, but the pace definitely appears to be picking up.

Yes, real estate agents are getting more “techy,” so to speak, yet there remains a divide between veteran agents who are entrenched in traditional marketing practices and recently licensed agents who exhibit an appetite for all things tech.  The state of real estate marketing is definitely trending tech however, whether agents are ready for it or not.

One evident reason for the boom of tech start-ups in real estate is due to the vast wealth the industry commands as a percentage of the nations total economic assets.  To be specific, residential homes account for the single largest “tangible” U.S. real estate asset, worth roughly $23 trillion.  Commercial real estate further accounts for another $15 trillion.  As an asset class, real estate is larger than other U.S. heavyweight industries such as fixed income, equity and health care.

So that being said, venture capitalists continue to swarm into real estate to get a piece of the action and capitalize off of the tech boom that’s quite unrealized in real estate. Venture funding of real estate technology startups reached a peak in the Q4 of 2014, with 32 companies raising around $300 million. In total, venture funds have invested $605 million in real estate startups in 2014 versus $241 million in 2013 – a growth of more than 250%. There are a number of signs suggesting the trend will continue through the remainder of the year.

While Zillow continues to grow it’s batch of proprietary technology with the recent acquisition of Trulia, real estate technology is indeed growing at a rapid pace.  New predictive marketing companies like Smartzip, ReboGateway, and My Listings Agent, promise real estate agents high quality leads using big data and predictive analytics.  Will simple web advertising on Zillow continue to satisfy the marketing demands of real estate agents, or will the predictive power of big data attract agents to sites like My Listings Agent?  It is indeed the dawning of a new tech age!



Is Zillow Beginning to Fizzle?

Zillow appears to have strengthened its position as the top-dog of online property search websites with the acquisition of their closest rival, Trulia. However, ongoing legal troubles with Move, Inc.’s® and the severed syndication deal with ListHub highlight some immediate concerns for the most trafficked website in all of real estate.


While Zillow still attracts an enormous amount of users to it’s website (Ranked 35th in the U.S. according to, A recent downgrade by Barclays cites “slowing web traffic growth” as the biggest long-term concern for Zillow. Zillow’s impressive valuation was based on the notion of improving web traffic, driving user engagement, and providing a quality marketing platform that allows agents to market their business on the internet in a cost effective manner – So let’s see how they’ve been doing…

Real estate agents are crying foul over Zillow’s outrageously expensive ad offerings.  Many agents have long complained that buyer/seller leads from websites like Zillow and Trulia are low converting and disproportionately expensive.

Over the last few years, dozens of real estate tech startups have formed, promising agents a more effective way to find clients and generate leads.  Websites like Smartzip and My Listings Agent say they use the power of big data and predictive analytics to do just that.

While the successes of big data and predictive analytics are widespread and heavily applied in marketing, it’s particular application for real estate agents remains largely unrealized.  These websites claim to be able to predict who is likely to sell their home next, allowing agents to target their marketing specifically to the homeowners that are most likely to respond to their flyer, mailer, etc.  Vanessa Browne, a Realty One Agent out of Temecula, California says, “I think agents are reverting back to the tried and tested ways of generating, like walking the neighborhood and interacting with homeowners face to face.”

Agents are trending away from expensive and ineffective internet marketing and are instead relying on the innovation of companies like My Listings Agent to generate leads at a fraction of the price. “Instead of knocking on every single door when I go out, I first use My Listings Agent to find the names and addresses of the homeowners that are most likely to sell their home,” says Vanessa.

It is important to recognize the challenge Zillow faces in the future.  Current and future generations of real estate agents and brokers will continue to use the most cost-effective and efficient way to market their services; Zillow seems to be down but not quite out. The rapid pace of technological development forces companies to be constantly innovating or fall by the wayside. Will companies like Smartzip and My Listings Agent revolutionize real estate marketing or will Zillow find a way to buck the trend? One thing is certain, competition sure promotes innovation!