Track record / methodology

/ weather_rain

Typical horizon: MULTI-DAY • Season 1 — all time

What it does

Prices Kalshi's daily "will it rain?" binaries from NWS probability-of-precipitation forecasts for the settlement station, buying whichever side the market underprices by a wide margin. Logs every PoP so calibration is measured, not assumed.

Key parameters

behavior-shaping settings only
count 1
min_edge 15

Record (fee-inclusive, this season)

W–L
19–61
Open
4
Positions
84
Realized
$1.16
Marked
$3.23
Fees
$2.13

Calibration

predicted vs realized win rate, by confidence bucket
bucket 2 10 signals p̂ 0.18 → 0.0
bucket 3 23 signals p̂ 0.24 → 0.13
bucket 4 16 signals p̂ 0.35 → 0.13
bucket 5 15 signals p̂ 0.45 → 0.2
bucket 6 9 signals p̂ 0.56 → 0.44
bucket 7 10 signals p̂ 0.65 → 0.6
bucket 8 9 signals p̂ 0.76 → 0.56
bucket 9 3 signals p̂ 0.85 → 0.33
bucket 10 3 signals p̂ 0.94 → 0.0
Caveats: All results shown are simulated (paper) trading performance, not actual trading, unless explicitly labeled live. Fees and slippage are modeled (Kalshi's taker fee formula plus 1¢ slippage), which cannot fully reflect real market impact or liquidity constraints. Past performance, simulated or actual, is not indicative of future results. Parameters shown are the current configuration and change over time as the strategy is tuned. Nothing on this page is investment advice — see the full disclaimer.