When you’re the host of a convention, who do you introduce to a person you’ve just met? Are the person’s knowledge and experience the main predictors of a valuable connection? How do you leverage technology to facilitate serendipitous encounters?
These are the questions we are facing. In a small trilogy of blogs I’ll shed light on the process of translating a grand vision into actual physical encounters using artificial intelligence. In the third blog I want to talk about some exciting future developments.
I name thee OBER
Respecting a young tradition in A.I., I thought it appropriate to give the learning system a name. Your recommendations will be served by OBER, short for Ontology Based Engine for Recommending People, Places and Events. With OBER on the brink of going live, I would like to take a moment to ponder about future developments and the implications for the Seats2meet ecosystem.
From data to insights
In the previous installment I posted two pictures of a collection of interconnected nodes. Although I think those are quite the sight, it needs some work before the raw data is turned into relevant insights. The goal is to create an instant overview of the knowledge footprint of your Seats2meet location with an emphasis on the aspects of your footprint that sets the location apart from the rest. The historical development of the footprint will also be accessible, giving you the tools to take advantage of trends.
OBER will keep track of how often a recommendation leads to a meeting request. The next step would be to measure how often meeting requests lead to actual meetings. The final step in the matchmaking pipeline is assessing the quality of the meeting after it took place. To be clear, it is not our intention to invite people to rate the other person’s behaviour or likability. Rather, we’d like to assess the quality of the matchmaking in terms of solving the issue you were dealing with. We understand that not every date leads to a loving marriage.
…enables evidence driven enhancements
Measuring thorougly opens doors for all sorts of interesting enhancements of OBER’s understanding of the world. What if we could include psychological characteristics in OBER’s input? There is no limit in exploring how we can leverage technology to facilitate serendipity.