Understanding Consumer Decision-Making Using Agent-Based Modeling
The marketing world has changed. Previously, we tended to assume a direct consequence of a marketing initiative on a consumer. We even proved it qualitatively and quantitatively. The trick was to scale the marketing initiative as widely as we could. We assumed that if one consumer sees an ad we know they like and buys a product, that getting as many consumers to see the ad would result in more consumers buying the product. However, this view fails to take into account the interaction effects that take place. Other factors besides our marketing initiative influence the consumer including: other ads, other competitors, other consumers. All these factors interact in complex ways. A consumer might reinterpret an ad for a child’s car seat after hearing a news segment on a recall of the same seat. With the advent of social media, this phenomenon (which was always present) has become more prominent. The interaction effect – for our purposes, the ‘forming of choice’ – is dynamic, constantly evolving, and non-linear. The effect results in the consumer reinterpreting an input in unpredictable ways. A bank ad about scale can seem impressive, but when they then close local branches, it is reinterpreted as arrogant. This happened to Barclays after they ran the ad campaign in the video below. So significant is this interaction effect, especially now, that the old way of thinking is just irrelevant. We can’t expect to get focus groups
together, show them an ad, and then run a campaign assuming that the focus group reaction represents the market. We have to look at the market and try and understand it as a dynamic system and view our role as marketers as contributors to, but not controllers of, the system. So we have to understand the consequences, direct and indirect, of our actions within the entire system, not just on the individual consumer. The goal of using agent-based modeling in marketing is to understand the way in which consumer markets work as systems and help plan our optimal role within them. Consumers to us represent uncontrollable interactions within a system, and we simply have to try and predict these interactions and adjust accordingly. To do this successfully, we have to embrace the complexity of the system, not try and dumb it down. Based in Cambridge, Massachusetts, Greg Silverman is the CEO of Concentric, a company empowering their customers to create innovative and breakthrough strategies through the use of agent-based modeling and complexity science. Connect with him on LinkedIn here. Photo Credit
Complexity Is Us
An alternative, or perhaps complementary, explanation to the observation that mentions of complexity have been decreasing in recent years according to Google’s Ngram viewer, is that complexity concepts have become pervasive.
It was just days ago that I discovered Google’s Ngram viewer and started playing with it. For those unfamiliar with it, the Ngram viewer searches a huge database of books for occurrences of expressions that can contain multiple words, and plots the fraction of books in which the expression occurred in a given year. So I tried “Bonabeau”, one of the most important terms to me. No luck. I should instead keep Googling myself. I then tested “complexity science” and “complex adaptive systems”, which produced the fascinating diagram below: both terms take off in the early 1980’s, although complex adaptive systems have been around for longer, probably driven by the cybernetics movement. I suspect that the Santa Fe Institute, founded in 1984, is the catalyst for this exponential increase in attention. But somewhere around 2005-2006, the trends is reversed for both terms.
The ominous panda generator and the addictive baby naming site Nymbler are two examples of what we, at Icosystem, call the Hunch Engine™. When searching for a baby name (or an ominous-looking panda), you don’t really know what you are looking for. Hopefully you’ll know it when you see it. But random-walking through the vast universe of baby names (and panda faces) can become rapidly boring, and unlikely to produce a real breakthrough. Have you noticed, for example, that most baby-naming books list names in alphabetical order? By the time you have reached the letter C, you no longer want to have a baby. Instead, Nymbler follows your hunches: I kind of like Ivy and Lily, but not enough to name my baby girl Ivy or Lily. On the other hand I do hate Amanda – reminds me of a pest back when I was in second grade. These are feelings and hunches. How can we leverage them? The Hunch Engine uses a computational technique known as “interactive genetic algorithms” (the idea for which was first mentioned in Richard Dawkins’ The Blind Watchmaker). Genetic algorithms mimic the process of evolution by mutating and recombining the best members of a generation (Ivy and Lily) and making sure the worst has not offspring (sorry Amanda!). With interactive genetic algorithms, the user tells the machine what’s good and what’s not. For example, by picking Ivy and Lily, you are implicitly driving the hunch engine toward flower names –even though you may not have realized it before. And within a few clicks, you will have found Rosemary, the name you really wanted without knowing it. The secret, however, is that the hunch engine is constantly adding “noise” to your choices, trying to expand your horizon while at the same time offering variations on your selections. The whole becomes a source of serendipitous encounters. Situations where we don’t know what we are looking for abound. Beyond baby names, you may be looking for a name for your pet, your company, your product or your website. You just want to escape for a few days but don’t know where, and you don’t know what might be available at a reasonable price. Or you’re in the mood to go out tonight and would like to explore options. Or you’d like to design your own wallpaper but don’t know how to explore all possibilities. More generally, product configurators (for cellphones, computers or jeans) are usually limited or daunting. Or you’re looking for a tie to go with your new shirt: here again, have you ever tried shopping for ties online? Spend ten minutes and you’re left feeling dizzy. Yes, we even have a Hunch Engine for shopping for ties!
These are all examples where you would like to explore the space of the possible but it’s a really, really big space. The solution consists of outsourcing your left brain to the algorithm and maintaining right-brain control over what’s interesting – and what’s not. This division of labor between human and machine combines what machines are best at (sifting through lots and lots of stuff) with what humans are best at (finding patterns and using our experience and feelings). The Hunch Engine covers a continuum of situations, ranging from search (for example, finding a baby name) to design (for example, create your own wallpaper or a name for your company). As such, it is a form of intelligent design by means of evolution.
Icosystem Corporation •
222 Third Street, Suite 0142,
Cambridge, MA 02142 •
Voice: (617) 520 1000