deep-dive

How Kronos Normalizes and Denormalizes Price Data During Prediction

April 10, 2026 shiyu-coder/Kronos ↗

Kronos automatically applies z-score normalization to input price series before inference and reverses the transformation on model outputs using the per-series mean and standard deviation calculated from the historical window.

The KronosPredictor class in the shiyu-coder/Kronos repository handles all price data preprocessing internally. Whether running single-series prediction or batch inference, the framework ensures the autoregressive model receives standardized inputs while returning forecasts in the original price units.

The Normalization Pipeline in KronosPredictor

The normalization workflow lives in model/kronos.py and executes

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:

curl -s "https://instagit.com/install.md"

Add to your MCP client configuration:

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}

Ask your agent:

"Use Instagit MCP to understand how shiyu-coder/Kronos works."

Works with

Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →