While, a lot of marketing dollars have moved to new online avenues, which includes OTT programming; television advertisements still commands billion of dollars every year.

So far, the ad spots is placed in a very generic way, like connecting X to Y.

If there is a family soap opera, it wont have energy drinks ads. On a football match day, the adverts would not consist of the beauty soaps one. While the truth is human behaviour is not so consistent as connecting “X to Y”.

It would not be an exaggeration to say, current way of placing the adverts in television programming is like the proverbial, “blind man leading the elephant”.

The billion dollar problem in television ads marketing is to connect the human behaviour to ads. And in such a way that, ads translate in to valuable actions for the brand.

Machine Learning is now trying to connect the consumer behaviour with TV viewing. This do of course, includes the advertisement angle. EDO, a New York and Los Angeles based startup is trying to do this.

The way it is trying to solve the riddle is by watching television feeds in a giant DVR farm. And figuring out how ads correlate and cause consumer buying behaviour online.

EDO’s DVRs have captured 47 million “airings” of television ad spots over the past three and a half years. This database of ads compares against publicly available data of things people do online such as searching by keyword or looking up things in Wikipedia. A data set of “trillions” of consumer actions.

The data science matches between the airing of an ad and the spike in behaviour of various kinds that relates to that product or brand. Creating a kind of “A/B testing,” seeing which spots among several from a brand marketer had the biggest boost to behavior (source).

While it is easy to some extent to show correlation, showing causality is what is, the holy grail.