Today we're excited to announce our provisional patent application and paper on arXiv: GPTree<p>GPTree outperforms the randomness by ~10x and the world's best experts by ~3x.<p>The cool part is that:<p>1. It's explainable, not a blackbox. A decision tree that humans can understand.<p>2. Human-machine harmony wins over machine-only and human-only decision making processes.<p>3. It's potentially applicable and high performant to any decision making use-case.<p>We fine-tuned the model for our own use-case at Vela Partners, picking outlier startups at their inception stage.<p>The reason why we love this research problem is that humans are so bad at picking startups at their inception stage.<p>For context, only 2% of the US-based investor-backed startups become an outlier return at the inception stage. Y Combinator and tier-1 VCs hovers around ~3% and ~6%, respectively. Ten-fold cross-validated GPTree is at 8% and most fined-tuned version is at ~18%.<p>Please take a moment to take a deep breath and let that sync in...<p>GPTree can find 1 outlier startup out of 5 of its investments at the inception stage. This may translate into a 10x+ return fund for whoever uses it if the future behaves as it forecasts.<p>Excited to hear the HN's feedback.
I've been using some AI for evaluating company pitches and just digging details out of the diligence process. This is exciting.<p>Hard to see how AI can identify if the company is really innovative, novel. Or if it's a disruptive tech. How could AI even see that?<p>How can AI help determine the coachability of the team?<p>These seem like judgement calls that only humans can make.