Have you ever sat down to watch Netflix and been slightly concerned by some of the choices that flash up in the “recommended for you section”? The popularity of “Making a Murderer”, a legal documentary with Class- A levels of addictiveness has led to an awful lot of creepy looking criminals coming up on my screen as the recommendation system seeks to find my next hit.
I am not a crime documentary junkie but the choices make sense. The evolution of recommendation systems has come a long way over the past few years as more sophisticated techniques lead to ever greater subtlety to the recommendations, giving the user that “How did it know I liked that?” feeling.
Reducing irrelevance and guiding the customer through a journey of their own interests, experiences and habits makes the recommender modeller a powerful player in the online world.
If you are a Data Scientist experienced in building sizable recommendation models in a commercial environment then do get in touch. I have an awful lot of clients that would gladly appreciate the recommendation.
Recommendation systems are quickly becoming the new way users are exposed to the whole digital world through a prism of their own experiences, habits and interests. They are quickly evolving to be less obvious, more persuasive and far more useful, for both business and users.