--- url: "https://predictiontoolkit.com/tools/prediction-market-backtesting/" publisher: "PredictionToolkit" dateModified: "2026-11-02" --- [← Backtesting]() SDK # prediction-market-backtesting: Polymarket Replay and Portfolio Experiments prediction-market-backtesting is a developer-led Python/Rust research project built around NautilusTrader. It replays supported Polymarket vendor data and provides notebook runners, joint portfolios, optimization and detailed charts. [**3.5**/ 5Editorial rating]() [Editorial assessment]() [Open the prediction-market-backtesting repository]() github.com **Pricing:** [See plans and costs ↓]() [Screenshots]() [Explore alternatives]() [Backtesting]() [SDKs & libraries]() ## Screenshots and interface Product preview1 / 2 Overview of the research framework. ## What is prediction-market-backtesting? Choose PMXT or Telonex loading paths and preserve the selected schema, local layout and time range. Cached and materialized staging avoids repeated acquisition. Book deltas and trade ticks feed the event-driven simulation, where fees, latency and passive queue position remain explicit assumptions. Runnable public historical replay is focused on Polymarket. Kalshi code is research and fee-model plumbing; Limitless and Opinion remain planned. A separate BTC live-data sandbox is not the historical runner, and sandbox or live operations can require different accounts. ### Who it is for - Reusable Python replay research. - Comparing parameters across markets. - Inspecting execution assumptions and reports. ## Clients and supported operations - **NautilusTrader** Use the underlying event-driven simulation framework. - **Book replay** Combine supported book deltas and trade ticks. - **Vendor loaders** Documented PMXT and Telonex paths. - **Cached staging** Reuse local and materialized data. - **Joint portfolios** Model several markets with shared capital assumptions. - **Optimization** Explore parameters with supported samplers. - **Reports** Equity, drawdown, fills, allocation, returns and scoring charts. - **BTC sandbox** Separate live-data sandbox experimentation. ## Development workflows ### Reproduce an experiment Fix vendor, time range, runner and parameters; retain execution assumptions with results. ### Compare parameters Warm the cache, run the sampler and inspect unusual fills and drawdowns alongside return. ### Test a portfolio Use the joint runner to model capital allocation across markets together. ## Pricing and total cost The public repository has component-specific license notes. Data vendors, compute and separately enabled live operations have their own costs. ## Installation and configuration 1. Follow current setup and runner-contract documentation. 2. Select a supported Polymarket vendor. 3. Acquire or locate a small data window. 4. Run an example and inspect its report. 5. Specify fees, latency and passive-order assumptions. 6. Expand after single-market replay works. ## Useful links ### What to check - Limitless and Opinion are planned integrations. - Vendor schema and file layout must match the loader. - Queue position and latency are simulation assumptions. - Sandbox and live runners differ from historical replay and can need different accounts. A closer look ## Ratings & reviews Editorial rating **3.5**/ 5 0 user reviews PredictionToolkit editorial ### Our take on prediction-market-backtesting Vendor loaders and explicit assumptions offer substantial research tools. Data dependencies, component licenses and unfinished venue paths require developer-led evaluation. **Assessment criteria:** Task usefulness, documented scope, setup clarity, and access and cost transparency. **Assessment date:** 2026-10-01 **Documentation reviewed:** 2026-10-01 Documentation-based assessment. [How we rate]() ### User reviews 0 The main score switches to user ratings after 5 published reviews. **Be the first to share your experience** A specific example helps the next person choose the right tool. ## Related tools [Browse category]() ![Marketlens Python installation and Strategy quickstart]() ![Marketlens Python SDK logo]()[Marketlens Python SDK]() SDK**4.0**Editorial Compare fast bar experiments with detailed L2 replay, reusing downloaded history between strategy changes. - Language Python Compare a data-and-replay SDK. ![NautilusTrader Polymarket adapter scope and integration-guide entry]() ![NautilusTrader logo]()[NautilusTrader]() SDK**4.0**Editorial Receive native market events and manage signed orders, reconciliation and resolution in one trading framework. - Language Python · Rust Use the underlying simulation and trading framework. ![Public archive index showing PMXT V1 and V2 capture windows]() ![pmxt archive logo]()[pmxt archive]() Dataset**3.5**Editorial Download earlier Polymarket book captures from the public mirror and inspect the coverage of each era. Compare a historical capture source. ## Frequently asked questions about prediction-market-backtesting ### Can I immediately run a Kalshi backtest? No. The README separates its research plumbing from a runnable public path. ### Are notebooks supported? Yes. Notebook runners are documented. ### Can markets share capital? Yes. Joint multi-market runners are supported. ### Why can vendor results differ? Coverage, event ordering, depth and loader assumptions vary. In this profile