At a glance

Black Swan is a data-mining startup that works with big brands to predict product-based trends that exist in unstructured written social and online data. The company says its system is up to 90% accurate for up to a six month projection.

Why it matters

The startup’s capability comes from the natural language processing of massive amounts of unstructured data from social media, publishers, blogs, as well as historical records that helps it to model performance. It effectively gives brands a category-level view of the themes, ingredients, and ideas that are growing in popularity and the relative rate at which they’re growing. As direction or confirmation of new product developments, accurate forecasting in this way is invaluable.


  • Low-probability events are those for which we tend to not have enough data; predictions based on historical modelling can only take you so far.
  • Using a global focus group but without flawed questions, the firm is able to track and predict both the growth in interest of a trend and its lifetime.
  • Its capability stretches across client organisations: not only is it useful for marketers, but similarly for operations and supply chain investments.