Tools to Power Your Online Retail Business

eCommerce Journal

Subscribe to eCommerce Journal: eMailAlertsEmail Alerts newslettersWeekly Newsletters
Get eCommerce Journal: homepageHomepage mobileMobile rssRSS facebookFacebook twitterTwitter linkedinLinkedIn


eCommerce Journal Authors: Eric Horowitz, Mat Mathews, Jnan Dash, Jyoti Bansal, Steve Latham

Related Topics: iPhone Developer, eCommerce Journal, iPhone for Business, Married to Chocolate

Blog Feed Post

MAC Address Behavioral Analytics

I had the opportunity during a recent Big Data Vision Workshop to help a client determine where and how to leverage their wealth of anonymous MAC address data to support the organization’s key business initiatives. A very cool client with a lot of creative people always makes for a successful engagement, and this engagement was no different.

But before I dig into where and how your organization might be able to leverage location-centric data (e.g., MAC, beacon, Bluetooth, GPS), let’s review a MAC address.

MAC stands for “media access control.” A MAC address is a hardware identification

Figure 1: MAC Address

Figure 1: MAC Address

number that uniquely identifies each communication device (e.g., laptop, smartphone, tablet, smart watch) on a network. The MAC address is manufactured into every device and cannot be changed. Figure 1 shows a sample MAC Wi-Fi address for a smartphone.

To see the MAC address on your Apple iPhone, go to “Settings” and then “General” and then “About.” You will see something called a “Wi-Fi Address.” Yep, that uniquely identifies that device and enables organizations to uniquely track your device as it interacts with different wi-fi access points (in coffee shops, restaurants, malls, arenas, airports, etc.). Yep, I am officially known to Skynet as OC:D7:46:81:34:98.

Now analyzing anonymous MAC address data to uncover device behaviors, propensities and tendencies is not new. This is basically what web companies and e-commerce sites have been doing for years with anonymous website cookie data.

What is a Website Cookie?

A website cookie is a small piece of data stored in the visitor’s web browser. Every time that visitor visits a website, the browser sends the cookie back to the server to notify the website of the visitor’s previous activities (see Figure 2).

Figure 2: Sample of Laptop Cookies

Figure 2: Sample of Laptop Cookies

Much like how a MAC address cannot uniquely identify the user (me) and can only uniquely identify the device, websites cannot uniquely identify the user (unless you register on that website, like Facebook) and can only uniquely identify that particular device (laptop).

Cookies enable websites to remember visitor current state information (e.g., items added in the shopping cart), record the visitor’s browsing activity (e.g., pages visited) and determine visitor’s behavioral characteristics (e.g., product preferences, engagement tendencies, subjects of interest). These “Visitor Behavioral Analytics” enable websites and e-commerce sites to support the following types of analytics:

  • Personalized Marketing: enables creation of personalized ads and promotions based upon areas of interest and what similar visitors responded (Yahoo, Google, Facebook)
  • Product Recommendations: enables product and service recommendations based upon visitor’s interests and what similar others viewed or bought (Netflix, Amazon, Pandora)
  • Personalized Newsfeeds/Content: enables delivery of highly-relevant articles and news feeds based upon what the visitor previously read and enjoyed (liked, tweeted, shared)
  • Customer Service: capture support requests and browsing behaviors to predict product problems that customer support can resolve more quickly (Best Buy, Apple)
  • Sales Support: share visitor’s areas of interest so sales has a more well-rounded view of the customer even before first contact

MAC Address Analytic Profiles

We can apply many of the same website analytic techniques to the MAC Address data to provide many of the same benefits as cookies. We can create a detailed “MAC Address Analytic Profiles” for each unique and anonymous MAC address.

For example, let’s say that we are dealing with a large transportation port. With enough data over a long enough time period (think years, not weeks), we could derive for each MAC address profile the following information:

MAC 3

The analytic insights gleaned from the MAC Address Analytic Profiles could support multiple use cases including:

  • Traveler Segmentation Analysis
  • Campaign Effectiveness Analysis
  • Predict Terminal Passenger Volume
  • Predict Passenger/Terminal Transverse Flow
  • Predictive Facility Maintenance
  • Reducing Curbside Congestion
  • Increasing Tenant Revenue
  • Predict Ground Transport Needs
  • Support Surge Pricing
  • Support Sustainability
  • Many others…

MAC Address Example

Figure 3 shows a sample of what could be done with the MAC address data in tracking travelers and determining their preferences, tendencies and propensities.

Figure 3: Example MAC Address Travel Pattern

Figure 3: Example MAC Address Travel Pattern

Note: Figure 3 data and images are mocked up so as to hide the identity of the MAC address and the client (though it does look an awful lot like my travel patterns…)

Imagine having this level of insights into the patterns, propensities and behaviors of all the travelers, passengers, guests, players, visitors, students, citizens, etc. for a physical location (e.g., malls, arenas, ports, airports, department stores, campuses, cities). Imagine how much you could “improve the guest experience” if you knew more about your guests’ travel patterns, propensities and preferences. The potential to provide a more engaging and more profitable experience is almost unlimited.

The post MAC Address Behavioral Analytics appeared first on InFocus.

Read the original blog entry...

More Stories By William Schmarzo

Bill Schmarzo, author of “Big Data: Understanding How Data Powers Big Business”, is responsible for setting the strategy and defining the Big Data service line offerings and capabilities for the EMC Global Services organization. As part of Bill’s CTO charter, he is responsible for working with organizations to help them identify where and how to start their big data journeys. He’s written several white papers, avid blogger and is a frequent speaker on the use of Big Data and advanced analytics to power organization’s key business initiatives. He also teaches the “Big Data MBA” at the University of San Francisco School of Management.

Bill has nearly three decades of experience in data warehousing, BI and analytics. Bill authored EMC’s Vision Workshop methodology that links an organization’s strategic business initiatives with their supporting data and analytic requirements, and co-authored with Ralph Kimball a series of articles on analytic applications. Bill has served on The Data Warehouse Institute’s faculty as the head of the analytic applications curriculum.

Previously, Bill was the Vice President of Advertiser Analytics at Yahoo and the Vice President of Analytic Applications at Business Objects.