Part 2 The behavourial Data Science project – 5000 coefficients further than Ronaldo

Mastering behavioural data doesn’t get us to big influencers like football players such as Ronaldo, Microsoft giant Bill Gates or other famous personalities. No, since our first blog on his research study our investigator Joran has detected 5000 coefficients in the Netherlands based on online behaviour tests.  He focuses on the so-called average influencer.

We are convinced that Joran will eventually map the globe via everyone’s online behaviour.

It’s not about Ronaldo
First a short recap – Joran’s goal is to find a methodology for selecting personality datasets based on online behaviour. In other words: in his view the domain ‘extraversion’ can be determined based on who follows who combined with tweets and posts on social media platforms. His playing field is the enriched database with 350 million active social media accounts of MyScocialDatabase. 

One could easily argue that Ronaldo shows abundant extraversion and is the perfect exponent of this trait. But Joran is not looking for these extremities. For marketing reasons and a successful execution of campaigns you need the average influencer. Take a look at the photos and you will immediately recognise the practical insights he is collecting.

Screen Shot 2018-12-18 at 15.39.47.png

Mapping The Netherlands
Joran is about to scale up his model in order to come even closer to the precise coefficients. However, every researcher knows this is the most difficult phase. Playing around with an enormous database and test sets is one thing, finding the needle in the haystack is another thing. You need the special needles only to be able to come to the right path.

So, Joran is spending hours and hours in modeling training sets and finetuning his test sets in order to optimize his algorithm. And he’s getting somewhere! In a few weeks he will be able to map the entire online population of The Netherlands.  This micro map will become his bridge to conquer data on a global scale on human traits.