You're pledging to donate if the project hits its minimum goal and gets approved. If not, your funds will be returned.
$4,500 left to reach the funding goal.
This project builds an open prediction ledger that scores a correlational forecasting method in public. Forecasts, data sources, and scoring rules are published before outcomes are known, and results are published after, including misses, so anyone can judge whether the method works rather than taking my word for it.
Publish a dated ledger of forecasts with the data and correlations behind each one, score every forecast against what actually happens, and publish a final report that judges the method against simple baselines.
Success is a complete public ledger with every forecast scored, a clear comparison against simple baselines, and a written verdict on the method, whether the result is positive or negative.
The budget totals USD 4,500: data licences about USD 2,400, hosting and tooling about USD 900, documentation about USD 600, and reporting and contingency about USD 600. Spending will be tracked against this breakdown and reported publicly.
I am Alexander Garside, working solo on this project. I will publish the ledger, methods, and results openly so anyone can check the work and reproduce the scoring.
The method may score no better than simple baselines, data may be delayed or incomplete, or there may be too few forecasts to judge it fairly. If so, I will publish the negative result with the data and scoring behind it.
None. I have raised no money for this project in the last 12 months.