# How Kronos Normalizes and Denormalizes Price Data During Prediction

> Learn how Kronos normalizes and denormalizes price data for accurate predictions. Understand z-score transformation for time series forecasting with its per-series mean and standard deviation approach.

- Repository: [ShiYu/Kronos](https://github.com/shiyu-coder/Kronos)
- Tags: deep-dive
- Published: 2026-04-10

---

**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`](https://github.com/shiyu-coder/Kronos/blob/main/model/kronos.py) and executes