PredictionMarketBench
Unverified ML strategy on Multi by Oddpool. BotFinder score 18 out of 100.
A benchmark for backtesting prediction market trading agents using real Kalshi market replay data.
Source: github
BotFinder analysis pending.
PredictionMarketBench
PredictionMarketBench A benchmark for evaluating prediction market trading agents using real Kalshi market replay data. Overview PredictionMarketBench replays real Kalshi episodes and evaluates trading agent performance under realistic execution constraints. An "episode" is one Kalshi event with multiple tickers/markets. - Input: Recorded orderbook snapshots and trade prints from Kalshi - Agent: Implements a trading policy using provided market data tools - Output: Equity curve, PnL, Sharpe ratio, drawdown, and other metrics Installation Quick Start Agent Interface Agents implement the Agent base class: Context Methods The AgentContext provides these methods: | Method | Description | |--------|-------------| | getmarkets() | List of all markets with best bid/ask | | getorderbook(ticker, depth) | Full orderbook for a ticker | | getpositions() | Current positions per ticker | | getcash() | Cash and equity balances | | placeorder(order) | Submit an order | | getrestingorders() | View resting limit orders | | cancelorder(orderid) | Cancel a resting order | Order Types Included Episodes |
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)