this repo has no description
✨ Add example
+1
+1
Deep Funding.md
+1
Deep Funding.md
···
51
51
- Messy jurors have [disproportionate impact on the weights](https://davidgasquez.github.io/deepfunding-trial-data-analysis/#-robustness-checks)
52
52
- Weights are not consistent due to the limited amount of data collected and the variance on it
53
53
- Large graphs (hundreds of projects) make getting accurate weights from the pairwise evaluation infeasible
54
+
- E.g. GG24 round has ~100 projects and [would need ~ 3000 "actively sampled" comparisons to get to a relative error of 10%](https://arxiv.org/pdf/1505.01462)
54
55
- **Mechanism Settings**
55
56
- Some parameters have a large effect and haven't been adjusted
56
57
- The aggregation formula (huber, log loss, bradley terry, ...) has a very large impact on both modelers/traders and project rewards