prediction-market-analysis

To generate reproducible research artifacts from Polymarket and Kalshi datasets, this skill uses a Python-based analysis framework to process public market data. It outputs exportable charts, tables, and JSON files without executing any trades.

Yes, you can analyze prediction market data for financial research without executing trades. This skill specifically accesses public datasets from Polymarket and Kalshi to generate market analysis artifacts, ensuring research reproducibility for educational purposes.

To run Python-based prediction market analysis, you need Python 3.9 or higher and the uv package installed for dataset synchronization. Once configured, execute the 'make analyze' command in the cloned repository to generate the analysis artifacts.

The best way to export charts and tables from prediction market data is by running the 'make analyze' command. This framework automates artifact generation from Polymarket and Kalshi datasets, creating exportable files suitable for paid research outputs.

Yes, this prediction market analysis framework supports automated dataset synchronization. It requires the uv package to manage and sync large public datasets from Polymarket and Kalshi, ensuring your financial research outputs remain reproducible.