Bot for Kalshi
Asset-Class Specific Bots

EddieTGH / kalshi-weather-predictor

by Edmond Niu (EddieTGH)

Repository metadata checked 2026-09-23. GitHub was accessible; latest repository push: 2026-01-10. This does not verify current trading compatibility, security, or returns.

What it does

Custom temporal transformer ensemble with XGBoost. XGBoost achieves 1.55°F MAE; the custom temporal transformer achieves 1.0°F MAE. Optuna Bayesian hyperparameter search. Converts continuous forecasts to integer probability mass functions across bracket boundaries. Fractional Kelly with a 2% bankroll cap. Full frontend dashboard with auth.

What we learned from it

the accuracy ceiling on day-of weather forecasts is around 1°F MAE for the best ML models. That's tight enough to often pick the right 2°F bracket. If you're going to compete with this kind of bot, you need either a better model (hard) or different markets (easier).

Get the free weekly Kalshi flow report

One email every Monday with the past week's Kalshi activity: the largest fills, where size kept accumulating, the biggest movers, and the most traded markets. Numbers and tickers — no picks, no predictions.

You're on the list. The next report goes out Monday.

Don't want to maintain your own bot?

Bot for Kalshi is the no-code platform for automated prediction-market trading — visual builder, signals, encrypted credentials, kill switch. The infrastructure these open-source projects build, ready to use.

Start building →

One plan includes the visual builder, paper and live modes, hosted execution, and risk controls. Cancel anytime.