Improving the "Stickiness" of Your Website, Part 2: If They Like A and B, Would They Like "A+B"?
A few years ago, Heinz introduced a new product that was considered to be quite weird. The product was chocolate-flavored, blue-colored French fries, called Funky Fries. Heinz bet on combining some highly popular ideas:
- A huge army of consumers loves fries.
- An arguably even bigger crowd is a sucker for chocolate.
- Kids love color.
As you can guess (or already know), the product failed miserably. These ideas were so divergent that there was no synergy between them in the eyes of the consumers. Quite the opposite—by putting the conflicting ideas together, Heinz lost the appeal of both French fry munchers and chocolate connoisseurs, producing a negative effect. 
In the marketing lexicon, in a given situation when the reaction of consumers (their liking scores, purchase intent, and so on) to the messages (ideas, elements of a package or a web page, etc.) combined are not equal to the sum of the individual ratings, that's called an interaction. There are two kinds of interactions:
- Synergism. A positive interaction, in which consumers' liking of the combined offer is greater than the sum of individual item scores.
- Suppression. A negative interaction, in which consumers like the combined idea less than the sum of the individual liking scores of the components.
The problem lies in the sheer number of possible pairs of elements. For example, if we have six placeholders on a web page, with six possible alternatives for each placeholder, there are 540 possible pairs of elements.
This fact should explain why, until very recently, the effect of interactions either was ignored or was considered a middle ground between art and heavy statistics. In the latter case, it required an expert guess about possible significant pairs. Such alleged (guessed) interactions were then tested with consumers through a sophisticated statistical method of incorporating these pairs into the survey to confirm/reject the hypothesis. For years, market researchers tried to tackle this issue.  If the expert was right (or lucky) in foretelling the potential interactions, the results could lead to improved ideas. If not, too bad: Some great ideas might have been discarded unnoticed, or bad ideas went into production undetected.