Is There a Way to Reduce False Negatives?

We've had some interest from some of the folks that we work with on several things, like different stages. The first is basically, or like enterprise knowledge graft,. which is not really a data analytic question at the s a glance of it. But then the second part of that is to feed in some of the institutional data and try and derive and infer certain relationships around some of the projects. So i'm just curious if anyone has experience with that. What has been the experience?