# An open forecasting tournament on which combination trials will succeed

Source: https://onco.cc/ideas/idea-tr2-combination-forecast-tournament/  
OnCo record `idea-tr2-combination-forecast-tournament` (Idea). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Ask experts and models to predict, in public, which registered combination trials will meet their endpoint. Track who is right, and use the best forecasters to decide what to fund.

## Summary

Forecasting tournaments (Good Judgment Project, the replication-prediction markets in psychology) show that aggregated, scored predictions outperform committees. Applying this to registered oncology combination trials would create a calibrated prior for each combination, expose which mechanistic arguments actually predict success, and give funders a quantitative tool for prioritisation.

## Fields

- Kind: Idea
- Last checked: 2026-09-08
- Hypothesis: Aggregated tournament forecasts will discriminate successful from failed combination trials with an area under the curve above 0.75, better than expert panels or sponsor stage-gates.
- Rationale: Replication prediction markets forecast which psychology findings would replicate with roughly 70% accuracy. Trial outcomes are similarly forecastable from design, prior data and sponsor behaviour.
- Proposed test: Run a two-year tournament on 100 registered phase 2 and 3 combination trials with readouts due; score Brier and discrimination against outcomes.
- Maturity: speculative
- Actor: data

## Sources

- Bottleneck evidence (Too many combinations to test): Palmer & Sorger, Combination cancer therapy can confer benefit via patient-to-patient variability without drug additivity or synergy (Cell 2017): https://doi.org/10.1016/j.cell.2017.11.009

## Connected records

- collections: [ClinicalTrials.gov](https://onco.cc/collections/clinicaltrials-gov/)
- ideas: [An open engine that ranks every drug pair by predicted synergy before anyone runs a trial](https://onco.cc/ideas/idea-tr2-synergy-ranking-engine/)
- bottlenecks: [Funding follows fashion, not burden](https://onco.cc/bottlenecks/b-funding-allocation/), [Too many combinations to test](https://onco.cc/bottlenecks/b-combination-space/)
- key papers: [Combination Cancer Therapy Can Confer Benefit via Patient-to-Patient Variability without Drug Additivity or Synergy](https://onco.cc/key-papers/paper-palmer-cell/)

---
JSON: https://onco.cc/api/v1/entities/idea-tr2-combination-forecast-tournament.json