LP Login

Think Big. Move Fast.

In May I posted about a NY Times article that showed that making popularity data public made hits bigger and that talent was only one factor in this equation – the taste of the early adopters was more significant.

A recent Wharton research paper comes to a similar conclusion. Paid Content summarizes the results:

— “One, some common recommenders lead to a net reduction in average sales diversity. Because common recommenders (e.g., collaborative filters) recommend products based on sales and ratings, they cannot recommend products with limited historical data, even if they would be rated favorably. In turn, these recommenders can create a rich-get-richer effect for popular products and vice-versa for unpopular ones. This finding is often surprising to consumers who express that recommendations have helped them discover new products.
— In line with this, result two shows it is possible for individual-level diversity to increase but aggregate diversity to decrease; recommenders can push each person to new products, but they often push us toward the same new products.
— Result three finds that recommenders intensify the effects of chance events on market outcomes. At the product level, recommenders can ‘create hits’ out of products with early, high sales due to chance alone. At the market level, in individual sample paths it is possible to observe more diversity, even though on average diversity often decreases.
— Four, we show how basic design choices affect the outcome. Thus, managers can choose recommender designs that are more consistent with their sales or product assortment strategies.”

These are largely consistent with my conclusions from May for people who run social media sites:

1. If you’re trying to iterate towards a “best answer” then keep feedback loops to a minimum, at least before users “vote” on their own. (e.g. Hotornot, espgame)
2. If you’re trying to create “hits” out of some of your content (and don’t care if it’s the “most worthy” content – you only care that they are hits), then display feedback and popularity constantly, as this will effect user behavior and exacerbate the size of the hits (e.g. Youtube, Digg, American Idol?
3. If you want to “guide” user behavior in a certain direction, provide feedback that validates or shows the popularity of that behavior. This is consistent with my prior post on game mechanics applied to social media: keeping score.