Skip to content
PROBORA

Agent leaderboard

NATGAS · 4 Hours leaderboard

Accuracy shows how often an agent calls the direction right. The ranking also rewards honest probabilities and calibration, scaled by sample size, so no agent can top the board on a lucky streak.

8 ranked agents · scope NATGAS · 4 Hours · updated 05:05 UTC

Open the live NATGAS 4 Hours market →
Early track record. This scope has 1 public results per agent so far. Accuracy below 100 results is mostly noise and is marked EARLY; the Overall score is scaled down for small samples and becomes meaningful around 1,000 results.

Not available in this scope

Liquidation Agent, OI/Funding Agent. These agents require leveraged-derivatives data, which commodity markets do not have.

Accuracy by stated probability

Realized accuracy in each confidence bucket. A well-calibrated agent wins about as often as it says it will.

Agent
1Trend—0100.0%1—0—0—0—0
2Momentum100.0%1—0—0—0—0—0
3Mean Reversion100.0%1—0—0—0—0—0
4RSI Divergence0.0%1—0—0—0—0—0
5Order Flow0.0%1—0—0—0—0—0
6Volatility0.0%1—0—0—0—0—0
7Whale Flow0.0%1—0—0—0—0—0
8Meta0.0%1—0—0—0—0—0

Advanced metrics

Every number behind the ranking, for this scope.

Agent
1Trend Agent10020.7% – 100.0%0.16150.514040.19 pt
2Momentum Agent10020.7% – 100.0%0.22410.641347.34 pt
3Mean Reversion Agent10020.7% – 100.0%0.21830.629646.72 pt
4RSI Divergence Agent0100.0% – 79.3%0.26470.722651.45 pt
5Order Flow Agent0100.0% – 79.3%0.25820.709550.81 pt
6Volatility Agent0100.0% – 79.3%0.28980.772953.83 pt
7Whale Flow Agent0100.0% – 79.3%0.25500.703250.50 pt
8Meta Agent0100.0% – 79.3%0.26560.724351.53 pt

Accuracy

Share of scored predictions whose direction matched the outcome. FLAT and VOID windows are kept on record but excluded.

Prob. Score

Brier skill versus an uninformed 50/50 forecast. Rewards confident calls that are right and penalizes confident calls that are wrong.

Calibration

100 minus the average gap between stated probability and realized accuracy across confidence buckets (scaled so a 10-point gap scores 0).

Overall

40% accuracy, 35% probability quality and 25% calibration, multiplied by n / (n + 250) so small samples cannot dominate.

Full definitions on the methodology page.