backrecord.com - a tool for tracking opinions and predictions (opinions about what is going to happen in the future) of people in the public spotlight. Our goal is to help people form better opinions by providing easy access to the ideas in the first place alongside tools for assessing credibility. Our focus is very much on opinion, not news.
It's cool because I think it's an interesting and difficult problem and I don't know of anyone tackling it well. I still don't know how feasible it is to create an automated / crowd driven system that provides a measure of credibility that is reliable enough to be useful, but we are certainly giving it our best shot and I would love to use such a tool if it existed.
I also think it's cool because I think both our user credibility system and topic hierarchy concepts have aspects that are quite nice that I haven't seen elsewhere.
We are currently focused on finance because it is clear how to score predictions about things that trade in a market (though the problem is much trickier than you might first imagine). Also, it is clearly valuable if we can succeed, even in a small way which is the most likely outcome if we do. However, we are playing with features that have broader applicability as well.
It's cool because I think it's an interesting and difficult problem and I don't know of anyone tackling it well. I still don't know how feasible it is to create an automated / crowd driven system that provides a measure of credibility that is reliable enough to be useful, but we are certainly giving it our best shot and I would love to use such a tool if it existed.
I also think it's cool because I think both our user credibility system and topic hierarchy concepts have aspects that are quite nice that I haven't seen elsewhere.
We are currently focused on finance because it is clear how to score predictions about things that trade in a market (though the problem is much trickier than you might first imagine). Also, it is clearly valuable if we can succeed, even in a small way which is the most likely outcome if we do. However, we are playing with features that have broader applicability as well.