Paul M. Banas on Consumer Insights, Marketing Research, and the Digital Media Landscape
Random header image... Refresh for more!

Category — Search

Forecasting The Obvious With Google Insights For Search

Recently, Google announced a new forecasting feature for their useful Google Insights for Search.  At first blush, it would seem to be a great way to peer into the future and reach that nirvana of any good marketing researcher, the predictive insight.

However, after playing with the tool a bit, it’s not very clear that the utility of the forecasts is really anything more than a clearly laid out progression of obvious seasonality.

Here is a historical look at search behavior behind the term hot dogs, with the dotted line representing a forecast of future search behavior.

Google Insights For Search Hot Dogs

Based upon a quick look at previous years, though, you would see that you don’t need a sophisticated model to predict that there should be a big spike in searching on the term “hot dogs” coinciding with the start of the grilling season around Memorial Day, peaking at 4th of July, and then tailing off through the rest of the summer.

That’s not to say that understanding seasonality isn’t important in search.  In fact, it can be critical to providing a baseline in identifying deviations from the forecast, which is where the true insight lies.

What would be a more interesting tool from Google would be something that clearly laid out the historical trend in search, and then showed where search patterns began to deviate from traditional seasonality, say a spike in “Hot Dog” searches in February that were the result of a particularly effective Superbowl ad.

One really shouldn’t look a gift horse in the mouth, especially when it’s one of the many excellent free tools that Google provides for better digital insights.  However, researchers need to be cognizant that just because an observation comes to a brand digitally, doesn’t mean that it’s automatically innovative and insightful.

Forecasting data that moves beyond the obvious should always be the goal.  Unfortunately, it’s not always easy, as Nobel Prize winning physicist Niels Bohr so humorously captured:

“Prediction is very difficult, especially of the future.”

September 27, 2009   2 Comments

Modeling Search Data For Predictive Insights


A great presentation last week by Bill Tancer of Hitwise Intelligence has broken me out of the winter posting doldrums.

His topic on levering search data for consumer insights is one of my key interest areas on the bleeding edge of marketing research, and he did a great job of demonstrating the predictive power of modeling search data trends.

One of his most compelling talking points, reflecting the current state of the economy, showed an updated chart from this older analysis on the correlation of unemployment website visits with actual unemployment claims.

Google has gone here before as well, with their demonstration of the Google Flu Trends application, and how search data can be predictive of CDC confirmation of regional flu outbreaks by a couple of weeks.

Both of these examples illustrate how the modeling of aggregated search queries can be an incredible source of insights into consumer intent.

There are a couple of white space areas for marketing research with search data, and all worthy of further pursuit.  For me these include:

  • Analyzing search terms associated with digital marketing campaigns at the metro area level in order to link digital behavior to a store level or DMA based marketing mix model.
  • Identifying the most predictive search terms (“grocery coupons”) that best correlate with widely tracked consumer attitude and behavior metrics (Conference Board’s Consumer Confidence Index) in order to understand where consumer sentiment is heading before the competition does.

For a better understanding of the modeling technique behind Google Flu Trends, download the PDF and Excel files that illustrate their method as it appeared in the February 19th issue of Nature.

March 30, 2009   No Comments

Search Engine Research 2.0

With the announcement of its innovative use of search data to track the spread of the common flu, Google Flu Trends has allowed Google to lever the enormous potential of search analysis in order to track the most viral (pardon the pun) of trends.

Search Engine Optimization 2.0 and Search Engine Marketing 2.0 as concepts have dominated digital media over the last couple of years.  And now with Google Flu Trends the concept of Search Engine Research 2.0 is truly coming into its own.

Google Flu Trends is based upon the aggregation and analysis of the search behavior of people who type the flu symptoms they are experiencing into Google in order to confirm their self diagnosis and to look up potential treatment options.

Google has found there is a close relationship between the amount of people searching on flu symptom related keywords and the amount who actually have the flu itself.

In the chart above you can see how Google Flu Trends has been well correlated with data from the Center of Disease Control on the level of flu cases being reported in the US over the past several years.

The advantage with Google Flu Trends is that the data is available a couple of weeks ahead of what the CDC compiles and announces.

Google Flu Trends is a good demonstration of the potential of the large and relatively untapped potential of levering search data for marketing research and consumer insights.

I look at what Google is doing with its Flu Trends tracker as bit of kicking the tires and taking their data for a test drive around the block.

When researchers finally take this information out on to open road and push things to the limit, that’s when we will really start realizing the full potential of search engine research.

November 14, 2008   No Comments

Search Segmentation: Yahoo! Versus Google

I’ve said before “You are what you search for”; now it seems “You are what you search with”.

Heather Hopkins at Hitwise Intelligence has done an interesting analysis by filtering Yahoo! searchers and Google searchers through Mosaic’s cluster distribution groups to find out which type of searchers spend big dollars online. It seems Google searchers had a greater tendency to spend at least $500 online in the past month (larger bubbles further down the X axis).


What is also interesting, if you know a bit about Mosaic cluster definitions, is how Yahoo! has a more rural U.S. and downscale urban concentration, while Google reflects such clusters as Affluent Suburbia and Upscale America.

To my earlier post, my guess is that we would find significantly more “Natural Born Clickers” on Yahoo!, than searching through Google.

February 16, 2008   4 Comments

The Future Of Web Research Through Search Visualization

While Google is really good at answering facts by pointing you in the direction of the best authority sites, it can be fairly time consuming to do marketing research on broader themes like “Banner Advertising” or “Retail Shopping Trends” and quickly assemble and visualize groups of links from a wide range of sources on your topic.

If your topic is broad and popular enough, something like Yahoo’s directory can help, but many times it can become too focused on one or two static authority sites. can also help, but you need to learn to use it less like a bookmark repository and more like a social link referral service. Additionally, in its current state, it is just as “lines of text” driven as Google.

In this recent post at Social Media and Green Horses, robojiannis provides an interesting overview of the attributes of Web 3.0 or the Semantic Web and where it could go. He also asks what else we would want on the wish list for its future development.

For me, a better way to visualize search results would be the most useful development in the Web 3.0 future. Rather than focus on lists of single links and pages, I want to see clusters of links, or something I call link knots, that not only show you authority sites with relevant info, but how they are clustered with many other relevant sites on your main topic and side topics.

A couple of examples that hint at what I mean by this concept of link knots are attached below. As I work through this in more detail, I’ll post more.

TouchGraph, KartOO, and Quintura are all good starts at hinting at link knots, but they are all lacking some of the fluidity and scale I’m looking for from the future of visual search.

This example of Microsoft’s Seadragon technology is more related to a way to show visual relationships between photos and images on the web versus search results, but the fluidity of the technology demonstrated in this clip is truly stunning. Blaise Aguera y Arcas’ discussion of the most relevant application to something like link knotting is about 5:30 minutes into the clip.

YouTube Preview Image

Any other examples that people could share in this area would be appreciated.

January 20, 2008   4 Comments

What’s In Your Google Shadow?

Everyone has said or written something they later regretted. However, for most things, people forgive, they forget, they move on. For many things we regret saying, there isn’t a public record, only a private one between individuals. There is no personal court reporter making transcriptions of everything we say in person, or on the phone, or write on a post-it note.

That was true until Google, however, and the creation of your own personal Google Shadow. Your Google Shadow is the lifetime collection of all the information you have ever posted to the web. Everyone post written, blog comment made, rant delivered, or complaint aired is quietly and efficiently stored in search servers around the world. It will probably still be there for your great-great-grandchildren to see, long after you are gone.

Jeff Jarvis at Buzz Machine writes about how the relatively positive benefits of a life online outweigh the trouble your Google Shadow can cause you. While the embarrassing moments will be there for everyone to see forever, this is compensated by knowing that a virtual network of all the people you’ve ever known throughout your life is only a couple clicks away.

On the other hand, Max Fawcett at This Magazine talks about the negative tendency of Google Shadows to come back to haunt you. He also has a great quote from Douglas Coupland on living with your shadow:

“You’ve got this thing that follows you no matter where you go. It’s going to survive your real shadow long after you’re dead. It’s composed of truth, half-truth, lies, vengeance, wishful thinking, accuracy, inaccuracy. It grows and grows and gets bigger. It’s you but it’s not you.”

Personally, I don’t think the existence of my Google shadow is a positive or a negative thing. It just is.

You can know that thirty years from now you can search and probably see some form every web site you’ve created, potentially every Flickr photo you shared, and any random blog comment you posted, all preserved forever, courtesy of Google and the rest of the search engines.

It doesn’t make me want to pull the plug and live in a cave. However, it does kind of make me pause and think a bit before hitting publish.

January 8, 2008   1 Comment

Predicting Behavior Through Search Analysis

Just read a very interesting and well written piece by Oliver Burkeman at the Guardian on the ability of aggregated search data to potentially predict future behavior and attitudes.

He cites my favorite concept from John Battelle’s book The Search, which is about how the clickstreams of queries behind search creates a “Database of Intentions”. I’ve posted before on how this could revolutionize the fields of cultural anthropology and consumer research.

If you haven’t read The Search, it should be at the top of your list for reading in 2008. A truly fascinating book.

January 2, 2008   No Comments

Google is Everywhere

How does a company based upon a relatively simple service premise become so influential, such that its mere presence in a tangential category or industry creates changes that the current market leaders couldn’t or wouldn’t have ever anticipated?

On the surface, Google is a provider of information through its search services, a lot like an electronic version of an everyday library. However, the reason it has over $200 billion in market capitalization is because of advertising. And because it’s delivering very effective advertising, traditional advertisers such as TV channels and newspapers are either shifting their business models or slowly dying on the vine, all because of search.

Also, since the future of search will be moving from desktop computers to more mobile devices, Google is interested in the mobile marketplace. Which explains why this information provider is now developing an open source mobile software platform (Android) and bidding in the upcoming FCC wireless spectrum auction against such telecom giants as AT&T and Verizon. And because of its mere interest in this tangential market, Verizon just announced a previously unthinkable (for them at least) opening of its wireless networks to competitors’ mobile devices and software.

In addition, as this information provider has moved from search to advertising to telecommunications and many other ventures, its servers which power its services are consuming energy in incredible amounts. In fact, it is building facilities next to power generation sources just so it can be first in line for raw energy. So now Google is very concerned about an area that has previously been the focus of public and private utilities, as it explores such things as renewable energy through its RE<C initiative. And, as John Battelle cites in his Search blog, energy consumption could represent 20 to 30 percent of Google’s cost of goods sold in 2008.

So where does Google go from here? What’s interesting is that if Google can’t stimulate the innovation necessary in green power generation, than its interest in the politics of energy will also increase. What happens to the price of oil based upon events in the Middle East could suddenly be of great interest to Google. Next stop, Washington D.C.

All because a once little search engine went from providing information, to advertising, to telecommunications, to the energy that powers it all.

Not so much like library anymore.

November 30, 2007   No Comments

Search and CPG Brands

Consumers don’t spend a lot of time thinking about brands. Certainly not as much as marketers in consumer packaged goods would like them to. Consequently, a consumers’ search behavior focuses more on the behaviors, attitudes and need states a brand is associated with, versus anything about the actual brand. Matt Wilburn from Yahoo describes it this way in a research summary posted on Mediapost’s Online Media Daily:

“It’s not just consumers searching for brand names,” added Wilburn. “That does happen, but this research illustrates that consumers are meeting a broader set of needs through search. They’re searching for products that can answer lifestyle questions like ‘I have hair loss,’ or ‘I’m fighting wrinkles’–and life stage questions like ‘I’m going away to college’ or ‘I just bought a home.’”

Sometimes the most important consumer insights about a brand can be heard by listening to the side conversations about the needs and wants that set the context for the brand, rather than waiting to hear what consumers say about the brand itself.

October 24, 2007   No Comments

The Enormity of Search

Two big numbers jump out from this press release from comScore on the worldwide scope of search: 750 million people conducted 61 billion searches in the month of August. These data points from their qSearch 2.0 service show just how big the Database of Intentions has grown and subsequently the potential of search to gain insights into human behavior and belief systems.

October 23, 2007   No Comments