Personalized agent recommender systems in real estate

Personalization in product recommender systems in industries outside of real estate will soon impact how consumers choose—or will want to choose—real estate professionals on brokerage sites. The basic concept: How would Amazon.com recommend a real estate professional? To answer this there are two basic sides to consider: customer behavior within a system (and increasingly outside of the system; see what RETargeter is doing) and attributes and behavior of the real estate professional.

At a very basic level, recommender systems track and log consumer behavior and then match appropriate products and services based on this behavior. The key is that these products and services have particular attributes that “match” the behavior of the consumer. For example, assume Consumer A purchased five historical novels over the past five months, a recommender system likely would recommend another historical novel as a next purchase. So how could this impact real estate professionals?

First, assume a brokerage has a system that logs consumer behavior (login times, locations searched, favorite properties, map searches generated, etc). Second, assume a brokerage has segmented its agent base by basic factors (such as top neighborhoods serviced by the agents, top 10 zip codes serviced by the agents, lifestyle attributes, designation, luxury expert, waterfront expert, client service satisfaction ratings, MLS performance, etc). Next, the real estate professional recommender system could work similarly as to how a book recommender system works. And I know that some listing aggregators already offer this type of service, but these services on generally pay-to-play. What I am suggesting is that brokerages need to do something similar with their system and offer it free-of-charge to their agents.

For example, lets assume Consumer B registers and saves a luxury property overlooking a lake, the system could automatically “recommend” agents who work the zip code of luxury property AND are luxury agents AND are waterfront specialists. Next, let’s assume Consumer B clicks the profiles of each of the recommended agents, he or she will then see overall performance ratings, specific testimonials, and specific customer satisfaction ratings. The benefit to the consumer is that they’re presented with the “best” professional based on their interest, which supports customers-for-life marketing best practices. The benefit to the real estate professional is that they’re in front of the consumer faster and in context to the search process. This type of a process promotes a personalized experience which is key factor in capturing consumer mindshare. And, indeed, there is research that supports this proposition.

Value based CRM aligning marketing IT and finance functions

This article discusses values-based CRM concepts in regards to aligning marketing, IT, and financial functions. An interesting point made by the authors

[F]ocusing just on the ability of IT to support strategy and processes bears the risk of not utilizing the full potential of innovative technologies[.]

It’s clear there is a critical interdependence between both marketing and IT departments. As marketing seeks to “engage,” “relate with,” and “delight” customers in the continuous battle for share-of-mind and share-of-heart, relegating IT to the sidelines as bench support is not a good strategy. Rather, incorporating IT vision is a critical component in setting strategy. The complexity of consumer interactions with a firm’s brand, demands increasingly sophisticated infrastructure and data management tools to ensure that a firm can meet the needs of these consumers.

Similarly, firms ought to align financial management goals within this marketing-IT milieu. Financial concerns, in this context, center around setting proper marketing metrics to measure ROI and lifetime value of a customer. The paper points out that

[A] number of financial concepts (e.g. capital asset pricing model, portfolio theory, and real option approaches) have recently been transferred to customer portfolios…Such “marketing metrics”, based on these approaches and thus taking a future-oriented, long-term, cashflow oriented, and risk adjusted perspective, allow for an identification and measurement of the economic value contribution and the ROI of marketing[.]

To enable such penetrative insights, firms need to leverage data mining tools to create timely (i.e., near real-time) metrics to be shared across business to ensure uniform adherence to meeting clients’ expectations.

Consumer engagement and participation using QR

I thought this kiosk flyer below, which I found pinned to a wall somewhere in Estes Park, Colorado, is a novel use of QR.

QR Kiosk Flyer

 

What I like is how the purveyor has conveniently arrayed the subject matter. As a tourist, I especially liked the choices put before me and the prospect of interacting in an interesting way with the “place” the QR took me. And it is on this latter point where I was let down. The “Arts” QR simply took me to a website, listing a series of events with more links to click. Understandably, having this list of links is definitely a convenience and I would not have visited the site but for the QR. However, I cannot help but think that an opportunity was missed that could have “rewarded” or “delighted” or “surprised” me with some experiential marketing. For example, the QR could have landed me on a page inviting me to play a video that has interviews with local artists and events organizers…let me feel their passion, let me understand their love for their community…grab my engagement by letting me know the impact of my participation. Then I’d be much more likely to click the links related to each event. Further, since these arts events are seasonal, this is a process one can repeat. In real estate one could use QR in a similar manner by showcasing a homeowner interview, interviews with shop owners, or a narrated neighborhood tour. How do you/would you use QR?

Demographic shift, Google stealth social network, rich media

Three blog posts that recently piqued my interest:

Wake up, the demographic shift is flattening us. Although targeted at catalog marketing executives, what Kevin Hillstrom has to say is relevant to the marketer in us all. Here’s the essential take-away:

Right now, “The Big Shift” is steamrolling us.  We are essentially addressing the 55+ audience, and wondering why our businesses are eroding?  We must begin investing in the 18-44 year old audience, if we want to remain relevant in 2020, while optimizing profitability from catalog mailings to the 55+ audience.

Very poignant observation, and very applicable concepts to the real estate industry.

Is Google building a stealth social network? Well-reasoned argument that Google is doing this, and that Google’s +1 initiative is part of a series of tactics Google has recently deployed to continue playing its ground game in the social sphere.

Rich media + display ads + social = advertising perfect CTR-engagement metric storm? “Rich media” (aka multimedia) has been around for some time. Similarly, rich media has had periodic bursts of hype and utilization for over a decade (anyone who was in the email marketing space around 1998/1999 will recall the covey of rich media vendors present at the variety of “internet conferences” that occurred during the same time period). Well, it seems rich media is back again (like a poltergeist?) and advertisers seem excited (according to the article). What’s interesting to me is whether there’s an opportunity for enhanced engagement via a rich media ad conduit that will support social CRM initiatives.

 

Leveraging data analytics for competitive advantage

Two articles recently caught my interest. The first article from the Financial Times, Smarter leaders are betting big on data (registration required) focuses on how companies use data analytics for business intelligence purposes. The best quote from this article:

Data is the new plastics

The second article from the Los Angeles Times, He’s start-ups’ best friend, profiled angel investor Ron Conway and his theories about investing in start-ups. The most telling quote from this article:

His current focus is “real-time data” companies that help people share what they’re doing instantly – using text, photos and video. “This sector is going to be huge,” he said.

As real-time data begins to inundate firms more and more by virtue of their forays into the social web and mobile world, data analytics offers a way for firms to utilize this data in novel ways to deliver more engaging and relevant experiences to their customers. For example, a firm could use data analytics in a predictive manner to dynamically deliver more relevant web pages based on consumers’ behavior throughout a firm’s website. Similarly, firms can use a service like Flowtown in conjunction with a service like First American Core Logic’s lead qualification services to gain insight into a registrant by combining their social persona with their transactional persona and then deliver relevant data and content based on this combined persona. Firms that begin to leverage data analytics will have distinct advantages over their competition in the near and long-term future.

Obama Web 2.0 meets database marketing

Here are two salient take-aways from this great article detailing how Obama eviscerated previous fund-raising records

1) Strategically embrace Web 2.0 and facilitate consumer control over certain elements of an overall marketing plan

Supporters’ blogs and You Tube postings were also brought inside the campaign through the website, where the online team could help consolidate the energy and contacts generated by them.

2) Test, measure, refine, roll-out; keep what works, ditch what tanks; no “sacred cows”

[The new media team], meanwhile, was constantly testing different versions of its call-to-action pages, including requests for donations and voter registration. Did more people respond if it included video or text? Should the sign-up prompts be on the right column or in the center? Should they have a “learn more” button or direct sign-up? Once they discovered the most effective version, they replaced all the others with it. Among their lessons: Video can sometimes be a distraction rather than a help.

Measuring marketing influence

This research paper by Deloitte is an excellent summary of important considerations firms should make when re-valuing their marketing team’s contributions. The gist of the article is that it’s incumbent upon firms to set up a marketing measurement scorecard that accounts for the systemic impact marketing expenditures have on the bottom line.

The paper argues that the measurement system needs to go beyond typical CRM-system level reporting (i.e., moving beyond just measuring ROI as the primary indicator of marketing performance) and align with overall company strategy, account for competitive influences on a product or service’s marketplace success or failure, eliminate silos between separate business units, and measure across product development and roll-out lifecycles.

Planning longtail media campaigns with Google AdPlanner

Google’s AdPlanner (need to register for the beta) has the potential to unleash the power of traditional demographic marketing analysis to long-tail search strategies. This is a great tool because it allows media planners to target niche sites in a highly effective manner while focusing on distinct consumer segments. For example, let’s say that I’m targeting cycling enthusiasts and want to know which niche sites appeal to a male demographic with a HHI between $100,000 and $125,000. By using Google AdPlanner I have good idea where to start: roadbikereview.com and cyclingnews.com (see screenshot below).

GoogleAdPlanner

Zip+4 Targeting: Online Advertiser Demographic Segmentation

Assume you’re a brokerage firm with a wide distribution of properties over several zip codes. Aside from basic syndication to online aggregators, what’s another strategy to market your listings? One fee-based option that many aggregators offer is enhanced listings. Before you pay, however, ask them to prove their merit.

Assume you cover these two zip codes 28226 and 28104. According to Claritas, homes in these zip codes have very different consumer attributes (you’ll have to enter the zip codes yourself to get the results).

Armed with the demographic information, you should ask your online aggregator to give you a demographic break-down, at the zip+4 level, of it’s user audience on the search patterns and niche pages/sections of its site. For example, assume a consumer is searching an aggregator’s site in your coverage area (indicated by the consumer entering city name or 5-digit zip code as search criteria). Based on these entries, relevant properties are returned to the consumer. It’s at this moment aggregators give you an opportunity to have an enhanced listing display to this consumer.

Now it’s your turn to push back: ask for the historical demographic breakdown of the users who entered those search criteria: does the demographic base skew towards segment A (assume A is more likely to own an inexpensive American made car and have a household income below $50,000) or segment B (assume B is more likely to own an expensive foreign made car and belong to a country club)? Once you know, you will know which listings to enhance, while including appropriate imagery and content triggers that appeal to the lifestyle attributes of your targeted demographic segment.

For example, if the base skews towards segment B, perhaps you choose to only enhance listings that are 1) above $750,000, 2) close to a country club, and 3) have ample space for a boat.

Thus, you’re consolidating your advertising resources by focusing on high-gain marketing activities that give you a higher chance of getting a high quality click/lead. It’s a win for the advertiser too because they’re serving you better by giving you the opportunity to gain a high value click/lead (thus promoting retention of their services), while legitimately asking for a higher CPM or CPC for such.

Zip+4 Coding for Real Estate Listings

What does The Filter have to do with real estate search? (NOTE: I went through the The Filter Q&A and have to say it was eerily prescient).

What if there was a site where a consumer would 1) define the location where they want to live (via natural language, drop down, or map search), 2) answer a simple set of “lifestyle-oriented” questions, the answers to which would bump up against Claritas’ Prizm database and 3) where a real estate broker would have performed a similar zip+4 coding of their listings? When the consumer presses the “Go” button, the answers to the lifestyle questions would peg a PRIZM code to them (via session cookie or registration ID) that would relate to the same PRIZM code tagged to the properties and deliver only those matched properties to the consumer.

The benefit to the consumer is they’ve cut through gobs of listings that may not fit their lifestyle and found the ones that do. The benefit to the broker is they’ve delivered a high value service to the client. If the broker then had live chat, IM, or showing appointment booking features on each listing, there’s a higher chance of getting a conversation started and higher quality inquiry on the listing.
Right result, right time, right for the consumer.

Privacy and social networks

Research papers:

Identifying inherent privacy conflicts in social network sites

Assessing the privacy risk of sharing anonymized network data

Proposed algorithm for automatically extracting social hierarchy data from electronic communication behavior

Discusses how rumors, viruses, and ideas propagate over social social networks

Web 2.0 Digest 2008/1/2

When bloggers attack, has some great tips on how to respond to blogger swarm attacks. Many real estate firms are leery of bloggers and allowing their agents to blog; this post has some thought-provoking ideas on how to respond.

Interview with Jordan Behan explains how Web2.0 consumers are more informed in real estate search.

Another great post by MineThatData describes the difference basic differences between web analytics and multichannel analysis. The latter analysis lends itself to looking at the life time value of real estate consumers under the multi-generational marketing rubric rather than as one-off buyers that are forgotten as soon as a deal closes.

Here is a great post on how to build / support brands using Web 2.0 tools.

Engagement is the heart of any website. Occam’s Razor has an excellent post on the issues pertaining to creating a viable engagement metric or index.

(repost of 10/07/2007 entry)

Trulia Revenue Model, Part 2

At its core Trulia applies intense competitive pressure to traditional media firms that historically–in the collective sense–bilked real estate firms out of millions–if not billions–of dollars for essentially non-measureable advertising. Sure there’s the one-off case of a person who walks in the front door of a branch office clutching a Sunday advert who actually purchases a home. However, it’s much more likely that a buyer nowadays will visit a firm’s most important branch office–that firm’s website–when beginning a home search. Thus, with its launch, Trulia’s model filled a gaping advertising chasm essentially ignored by traditional media firms (i.e., sending targeted traffic to real estate websites), and these traditional media firms have since been scrambling to catch up (what’s wonderful to observe is that Trulia likely has around 100 employees and it’s seriously challenging traditional media firms for online advertising market-share dominance–REALTOR.com included–that collectively employ tens of thousands of employees. Such is the power of elegant code and focused leadership).

So where does Trulia reside in a modern media mix? As an advertising replacement to traditional media and / or REALTOR.com? For some firms absolutely. For other firms decidedly not. For some real estate firms the decision to go or not go with Trulia (or REALTOR.com, New York Times, etc) has been based on evidence. What evidence? Evidence derived from analyzing the quality of traffic / lead sources: in some cases it makes sense to stay with REALTOR.com, and in other cases to have Trulia replace both REALTOR.com and the New York Times as primary sources of traffic / leads. For the firms described, decisions were made based on data: traffic-source-to-agent-placement ratios, traffic-source-to-showing-appointment ratios, etc. In some cases Trulia won, in other cases it was REALTOR.com that won, and in still other cases it was the New York Times, etc. Nevertheless, it all netted down to what the data showed.

Accordingly, real estate firms looking for marketing solutions should find a set of tools that measures, quantifies, and interprets the data. What this means is that real estate firms need to wipe off the muck of data analytics myopia and embrace the basics: segment prospective consumers based on demographics and decide which set of demographics to serve (recite the old adage “You can’t be all things to all people” when doing this), apply the same analysis for each traffic / lead source (for example, Trulia may deliver higher quantities of urban young professionals, whereas REALTOR.com may deliver higher quantities of suburban soccer moms), determine what traffic / lead sources “convert” at the highest ratio per each segment targeted, apply these findings to the respective traffic / lead sources, and make an informed decision to stay with or abandon such as they apply to the targeted demographic.

Social network marketing corporate forays

Here’s a reason why Microsoft invested over $200 million in Facebook. It’s all about the data Facebook has compiled on its user base and the time this user base spends on Facebook. What’s the “veracity index” for this data? One assumes it’s higher than other data sources, since users’ incentives to enter data honestly is relatively high (why lie to my friends?, why lie about what interests I share with my friends?, etc). Accordingly, some companies are stumbling into this space, and getting ripped because of their stumbles. On the other hand, some other companies are “getting it” (looks like Target’s winning).
Obviously, these companies want to tap Facebook’s rich data stores and its users’ apparent nonchalance concerning how marketers will use such data within the Facebook community (read the comments in this post). Real estate firms (or agents or agent teams) interested in establishing a viable Facebook presence should follow Target’s model, rather than the seeming corporate topdown foray employed by Coke. This is not to say there are no strategy considerations; rather Coke’s plight is a cautionary tale that militates against myopically stumbling into the social networking space.

Real estate data integration for multi-channel marketing

The tightest definition of multichannel customer management I have yet found is:

Multichannel customer management refers to the design, deployment, coordination, and evaluation of channels through which firms and customers interact, with the goal of enhancing customer value through effective customer acquisition, retention, and development.

Neslin, et al. have authored a definitive research article that real estate firms can use to understand the challenges pertaining to “modern” real estate practices relating to client relationship, and agent relationship, issues. The research paper explores five primary challenges and analyzes the issues pertaining thereto.

Neslin begins by identifying the challenges:

[F]ive major challenges for managers: (1) data integration, (2) understanding consumer behavior, (3) channel evaluation, (4) allocation of resources across channels, and (5) coordination of channel strategies.

This post is first in a four or five part series that will explore Neslin’s position and extrapolate such to real estate marketing and client relationship best practices.

Neslin begins by identifying multitudinous ways by which consumers engage retail firms–from kiosks, call centers, catalogs, bricks-and-mortar stores, etc. Similar interaction vehicles are true for real estate firms–front-yard signs, websites, office walk-ins, etc. Next, Neslin defines “channel”

By “channel,” we mean a customer contact point, or a medium through which the firm and the customer interact.

He then sets the basis for his study: that the focuse of MCM is on the customer, as MCM is a customer-centric function. Neslin next identifies major phases of a client interaction

First, customer perceptions and preferences drive channel choices (e.g., the customer may prefer the Internet for search because it is easy to use). Second, the customer learns from and evaluates his or her experiences, which feed back into the perceptions and preferences that guide his or her next shopping task (e.g., the customer may learn that the Internet search did not answer all the important questions). Third, the customer chooses both channels and firms, so from the customer perspective, it is a two-dimensional choice.

The relevant question then is: to harness this consumer interaction data, what investments must a firm make regarding such? What Neslin argues is that firms do not necessarily have to invest in processes that involve “full data integration” in a quest to develop a “single view” of a customer. What this suggests, then, is that firms must make strategic investments in data acquisition a key points in a transaction.

Real estate firms can leverage key consumer data acquisition “channels” or points. First, any point where a consumer registers for information is a channel. This real estate site contains at least 15 registration opportunities for clients during key phases of a transaction: from beginning (click-to-chat) to contacting an agent to book a showing appointment. Of course, many firms already have this data. So what’s the next step?

Data overlays.

That is, real estate firms should consider augmenting this core consumer registration data with real time, or post-transaction data overlays, from data aggregation companies like Experian, Acxiom, Equifax, etc. These overlays take the form additional demographics, psychographics, household income levels, lifestage, etc, data elements.

Another form of consumer data can be supplied by real estate agents. Although somewhat rare, some agents actually keep client profiles (likes, desires, familial relationships). Why? Because thes agents know that understanding a client’s profile allows them to serve this client (and like clients) at a degree somewhat higher than the norm. These agents use these profiles as their competitive differentiator.

Creating client profiles (either at the per record level, or aggregate level) should be considered a first step for any real estate firm that’s serious about multi-channel management. By using such profiles firms can engage clients at a more relevant and informative level. Thus, maximizing the return on investment the customer is making by spending time on the real estate firm’s site. Similarly, a firm maximizes its own return on investment by allocating tight marketing resources in a more intelligent and cost-conscious manner.

Multichannel marketing forensics

Kevin Hillstrom, President of MineThatData has written an excellent whitepaper on conducting a multichannel forensics analysis. Why is this whitepaper an important resource to real estate firms? Because real estate firms are engaged in complex multichannel marketing endeavors. But only a handful of these firms analyze their data from a multichannel perspective.

How does a firm begin its forensics analysis? Hillstrom explains:

  1. Understand the Retention Mode your product, brand or channel resides in.
  2. Understand the Migration Mode your product, brand or channel resides in.
  3. Combine the Retention and Migration Mode, understand which of twelve retention/migration modes your business operates in. This determines the way you will grow your business, long-term.
  4. Map the Ecosystem, so that the executive can clearly understand how all products, brands and channels interact with each other.
  5. Forecast the Ecosystem. This allows the executive to understand the long-term health of the ecosystem, given various marketing initiatives.

A key point Hillstrom makes is to look at multichannel businesses as ecosystems, where each product and division is interdependent on one another (a biodiversity perspective would also apply). Unfortunately, many companies are still balkanized in this regard.

For the most part, real estate firms have at least centralized their focus around a core product and service: representing buyers and sellers of homes and other forms of real estate, combined with highly related ancillary businesses such as rentals, REO, mortgage and title services, etc. This is a real estate firm’s ecosystem.

Hillstrom, in this whitepaper, has identified several business modes and strategic considerations related thereto. With the exception of certain commercial divisions and investment services, real estate firms fall within one of the two following modes: Acquisition / Equilibrium Mode and Acquisition / Transfer Mode. Both modes imply a constant sourcing of new customers with differences in how customers adopt new products or services. In the case of the former, Hillstrom states customers occasionally migrate, whereas in the case of the latter, the assumption is that customers will migrate to another product (much like a professional baseball player over his career migrates between teams).

So how can real estate firms a) position their products and services more relevantly to new sources of customers while b) targeting the “may migrate” class to the “probably will transfer” segment? Hillstrom advocates mapping the ecosystem

A key aspect of Multichannel Forensics is the mapping of the ecosystem you work in. Each combination of products, brands and channels are mapped. Any relationships in equilibrium or transfer are mapped with arrows, arrows that indicate the direction of the relationship.

The next step is to forecast the ecosystem, which, Hillstrom argues, enables executives to engage in valuable scenario analyses.

The benefit to a real estate firm in undertaking these analytical steps is that it will have a deeper understanding as to how its agents influence (negatively or positively) the firm’s sales of its primary and ancillary products and services. What’s also beneficial about Hillstrom’s whitepaper is that he actually gives you a step-by-step process by which to perform the analysis.

Gatineau Project marketing metrics

Eric Peterson continues to provide great insight. He has an exclusive profile of the Microsoft Gatineau project. At first glance, the Gatineau project is quite impressive. What’s particularly pleasing is that it appears to have been designed for marketing personnel and business managers. The visual representation of the data clearly indicates relevant campaign success and failure metrics.

Nevertheless, there are some considerations: Will this service give an accurate, and full representation, of data across multiple universes, or is it just limited to the MSN universe? Can firms track their competitors with this program? And with respect to their demographic data, it seems to be self-reported data from MSN, rather than from a wider sample data set; thus, how representative is the demographic data in Gatineau?

Ceating an engagement index for real estate websites

As an increasing number of real estate firms seek to embrace and integrate Web 2.0 principles in to their websites, many of these firms may encounter a sense of frustration in having to “upgrade” once again to meet, or exceed, customer expectations regarding Internet-based services. Is real estate an Internet based service? Absolutely. With over 70% of real estate searches beginning on the Internet, real estate is decidedly an Internet-based services industry. But what kind of Internet-based services industry?

Rather than an “execute on what I already know” process, real estate is more weighted to a “search and gather” process. Few customers, in one search session, find a home, contact an agent, book a showing, and buy a house the next day. The majority of consumers spend several months, on average, searching for homes, viewing listings, compiling research, and saving preferred property listings before even registering with a firm or contacting an agent (i.e., searching and gathering). And real estate firms have tried to facilitate this search and gather process with their registration systems, drip marketing services, and online appointment making processes. But these tools align more with the “execute on what I already know” (i.e., utilitarian) aspect of the home search process; that is, these elements do not really help a customer determine what attributes to search for in home or community.

So, what should firms do to engage customers earlier and mid-way through the process to facilitate a higher degree of interaction with, and reliance on, the firm’s website to help a consumer define attributes? One way to begin is to set key performance indicators and develop an engagement index.

Creating an engagement index is a great way to assess overall site responsiveness to consumers’ search needs. Eric T. Peterson defines engagement as

Engagement is an estimate of the degree and depth of visitor interaction on the site against a clearly defined set of goals.

He has written a great series of posts on this topic. Part V of his series steps readers through the application of his process. Jeremiah Owyang adds some additional considerations here and here. And this blog actually walks through how to calculate “influence”.

Although these concepts in analytics may seem arcane, by focusing on such, real estate firms can begin the process of smoothly, logically, and economically moving their sites into the realm of Web 2.0. In future posts, I will explore how real estate firms may begin to create and apply an engagement index, and what elements they should focus on measuring regarding such.

Real estate technology adoption principles

In 2004, Inman News profiled e-mortgage processes. In the ensuing years, paperless mortgage processes have improved but have yet to achieve wide agent adoption rates, as do many other real estate technology initiatives (e.g., real estate ecommerce centers). Could this be a classic example of the Technology Acceptance Model theories at work? ( Wiki definition 1, Wiki definition 2, research paper).

Many real estate firms have invested thousands, if not hundreds of thousands of dollars, in improving their technology offerings for their agents, only to see these technology investments gather dust as seasoned agents largely ignore–or at least fail to take full advantage of–such offerings in favor of their offline processes. The TAM predicts that a user’s perceived value of a technology resource affects this user’s adoption of this technology.

Assume that a brokerage wants to increase Internet ecommerce center participation and satisfaction rate amongst its agent base. This strategy makes good sense, as most real estate consumers begin their searches online, prefer the Internet experience, and eventually work with a real estate agent.

At its base level, a real estate ecommerce center answers mundane questions, finds out where a consumer is in the buying process, helps the consumer sift through much of the generic real estate information, helps the consumer refine search criteria, and then refers this consumer to a real estate agent. At this point, many brokerages would assume it’s the agent’s business to lose. But is it?

Many agents understand this basic qualification service. And this is where these types of services generally stop…basic. In other words, agents still are doing much of the work with an Internet client, in terms of driving towards a conversion, after this consumer is “handed off” to them. Yet from a brokerage’s perspective it’s doing a great service to its real estate agents by funding, staffing, and managing such a service. As such, there is a mutual perceived lack of usefulness on both parties (the agent thinking it’s less useful than it is, the brokerage thinking it’s more useful than it is).

From the standpoint of the agent, perceived usefulness would likely increase if the brokerage did more qualitative analysis prior to a hand off. For example, at varying points in the qualification process, call center personnel can round-out a client’s profile by either entering in data as they converse with a client, or refer clients to online tools that allow them to provide additional profile information. This data would extend beyond such basics as purchase time-line, preferred home type, newsletter selections, etc, and delve into lifestyle, preferred community attributes, etc.

Additionally, a brokerage could append basic demographic data to its pre-transaction consumer file by either using a reverse append service (Experian and Acxiom offer reverse append services that can attach a postal address to a valid email address) or by keying off the postal address the consumer registered with; regardless as to how a postal address is sourced, a brokerage would then be able to overlay zip code-derived lifestyle / life-stage and other demographic data. This would then allow consumers to choose home-types based on lifestyle (the brokerage’s listings database having been similarly overlaid with lifestyle / life-stage data, which enables this type of matching to occur).

These types of fundamental direct marketing techniques drive towards one goal: to hand the real estate agent a consumer who is well-informed and ready to act. Since the brokerage has tracked all phases of the communication leading up to a hand-off, the brokerage can deliver a profile-based client dossier to the agent who can then take this information and better perform his/her roll as a real estate trusted advisor (i.e., the agent can initially engage the consumer with a knowledge and insight gained as if he/she had actually interviewed the client in depth). Thus, the real estate agent focuses on his/her core competency, which in turn reinforces the usefulness of the brokerage’s ecommerce initiatives and further lowers barriers to adoption.

Profiling hedonic data in social networks

Continuing the discussion from the McKinsey interview of Cammie Dunaway, she states

[Yahoo!] is using behavioral data–really mining the wealth of transactional data we have about how people are spending their time online and trying to marry that data with attitudinal data…that’s where the most powerful insights can really come from.

Insights into what? It could be many things. Two of the most studied motivational data elements are utilitarian motivations and hedonic motivations. Utilitarian motivations center around goal-oriented behavior (e.g., I logged in to check my email, I checked my email, I logged out). Hedonic motivations are more social in nature (e.g,. I logged in to explore, to analyze, to decide, to eventually take action).

In real estate search, companies have typically focused on rewarding utilitarian behavior, often in a very reactionary manner. Consumer searches site > Consumer registers > Consumer selects home > Consumer is “passed off” to a real estate agent. Of course, the ultimate goal is to consummate a sale. And improving the “experience” of looking for a home on a real estate firm’s website could actually lead to more loyalty, referrals, and sales.

Nevertheless, overly focusing on “experience” at the expense of a goal can scuttle both consumer loyalty and ROI. Thus, balance lies in properly testing and deploying Web 2.0 assets that fulfill consumer goals while logically jibing with the product subject matter.

So how does mining attitudinal data fit this balanced approach or paradigm? Incenting consumers to add profile information that logically fits a goal is one idea. For example, if a real estate firm’s goal was to create a social network on their site targeted at tapping a suburban soccer mom demographic looking to buy a home, logical profile information may be zip code (current residence and desired residence), schools, sports, design preferences, and home type.

Zip code is important because the firm could relate this consumer to an agent who serves that zip code, where the agent serves as the social network ombudsman(woman) to answer questions and otherwise kick-start the group. Secondly, once a firm understands home type preferences and desired location, the firm can relate specific home information, community information and statistics, and other moms in the network to this person. The additional profile information constitutes community building information (e.g., relating moms who have children in similar sports). These steps help build a community and take the burden off the real estate firm to be all things to all consumers (if a mom has questions about how her child can join a traveling baseball team, she could ask the real estate agent, but more likely she’d ask the community). This way the firm’s “social asset” reinforces the firm’s local expertise, which allows for an eventual monetization of this consumer as she “graduates” through the process into ultimately looking at home types and eventually purchasing a home.

Through the tracking of profile data combined with the interaction of the consumer with the group (communications, postings, etc) combined with accessing utilities (e.g., widget downloads pertaining to design elements, video home tours, community data, statistics, etc), a firm could create an “engagement” index to validate whether their site is properly satiating consumers’ needs (Circuit City does this). The experience of this for the consumer is not so much having real estate listings and drip marketing pushed her way, but related data presented in a way that allows her to more deeply engage in the process and begin building a community before actually living in a community. Finally, in terms life-time value, this type of a social network could operate as a forum for a firm–and its real estate agents–to cultivate a valid and meaningful long-term relationship with consumers after they have actually bought a home (thus, closing the circle by adding transactional data with previously compiled attitudinal data).

Trust indicators in social network marketing

Jeremiah Owyang explains the concepts and value of social networks from a marketing perspective in an easily digestible manner. Yang et al (registration required), Battiston et al, and Hill et al discuss the scientific underpinnings of these topics. Juxtaposing these discussions against one another leads to some interesting insights with respect to social media marketing.

Yang notes that in 1967, Stanley Milgram demonstrated that mutual acquaintances drive social network strength. As Yang elaborates:

“[T]he probability that two of someone’s friends know one another is much greater than than the probability that two people chosen randomly from the population know one another.”

Yang illustrates the concept of this theory by pointing to the success of Hotmail, which grew from 0 to 12 million users in 18 months.

Battiston explores how “trust” factors between actors in a social network affect the dynamics of recommendations in that social network.

“Trust plays a crucial role in the functioning of such socio-economic networks, not only by supporting the security of contracts [sic?] between agents, but also because agents rely on the expertise of other trusted agents in their decision-making.”

What Battiston drives towards is that trust-based modes of recommendation have an inverse relationship to traditional modes of recommendation, which are primarily based on the volume of recommendations as opposed to the value of recommendations. Battiston argues that trust-based (or value-based) recommendations are inherently better at promoting more satisfying results to actors within a social network.

This, in turn, promotes the propogation of sub-group cultures to form within the social network. And as non-trustworthy agents drop out of the network (because prior recommendations did not fulfill specific trust elements as dictated by the requesting actor), the sub-group refines itself overtime. As more sub-groups are defined within a social network, “network neighbors” emerge amongst members of these sub-groups, where these network neighbors operate as conduits between different sub-groups.

Yang demonstrates that sub-group performance, in terms of marketing results, out-performs all others (this was measured in terms of traditional transaction response rate metrics).

Accordingly, marketers must seek out sub-group network neighbors. These individuals are the brand influencers and advocates within a social network. Jerimiah Owyang has an excellent post on the visual display of this information. Leverage Software has developed a product which likely can visually display these sub-group cross-over individuals, thus making the selection of influencers and advocates easier. Perhaps these individuals would be great focus group candidates, “real time” collaborators in product development initiatives, etc?

Mining social network relationships

HitWise has demonstrated a correlation between LinkedIn and Gmail, YahooMail, and Hotmail and a corrleation between LinkedIn and Facebook. Hypothetically now…assume that LinkedIn and Facebook and Gmail, or YahooMail, or Hotmail share their databases, where a user’s email account address is the unique identifier. At this point it’s a matter of relational database mechanics to ascertain unique marketing–i.e., direct response, email, branding, etc–opportunities that these companies can exploit. What they (marketers, Facebook, Yahoo, etc) would likely look for would be “network neighbor” influencers (more on this in forthcoming posts).

ROI Conversations at Inman Connect

Notes from my presentation on ROI at the recent Inman Real Estate Connect conference:

Issue: What are the first steps real estate firms should take to get a handle on their data to enhance near-term and long-term ROI on this data?

  1. Since 80%+ of all originating real estate transactions begin on the Internet, firms should consider utilizing proven Internet analytics engines;
  2. Firms should create an existing consumer data warehouse that accepts data from whatever format and whatever source, normalizes this data, hygiene this data, to net down to a single record per consumer data set;
  3. Firms then should segment this data, overlay this data (e.g., with demographic or lifestage data), score and profile this data, and then model this data; this gives firms insight into their existing consumer data;
  4. This data warehouse then is used to drive marketing decisions pertaining to existing and emerging or new consumers.

VisiStat is a program to understand broad as well as locally-specific Internet use traffic that real estate firms can employ to make more informed decisions about how to manage their Internet resources, agent base, franchise locations, etc. The same can be said for Google Analytics, HitWise, etc.

But if we’re really focused on ROI, the key is consumer-specific data and the analysis of such. Accordingly, if one only looks at Internet based, or Internet derived traffic, it’s largely like looking at the top crust of an apple pie…the filling is where the substance is. And in the case of ROI that substance is a carefully constructed marketing database and marketing data warehouse where each consumer data record has been individually segmented, scored, and overlaid with demographic, psychographic, and lifestage data.