> ## Documentation Index
> Fetch the complete documentation index at: https://freelance-4888ed08.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> Release history, breaking changes, and upgrade guides for the Demand Forecasting System

## Release History

Track breaking changes, new features, and important updates to the system.

**v2.1.0**

February 2026

## New Features

* **Multi-objective Optuna training** — Optimize for both RMSE and MAE simultaneously
* **Ensemble model stacking** — CatBoost + XGBoost + LightGBM + Random Forest ensembles
* **A/B testing framework** — Route traffic between production and challenger models
* **Evidently drift monitoring** — Per-feature KS-test drift detection with configurable thresholds
* **Security middleware stack** — OWASP headers, rate limiting, trusted hosts, CORS

## Breaking Changes

> [!WARNING]
>
> The following changes require manual updates when upgrading from v2.0.x:

* `weekday` parameter key renamed to `day_of_week` in `parameters.yml`
* Demand lags changed from `[1, 2, 24]` to `[1, 2, 22, 23]`
* `RetrainingScheduler` class removed — replaced by Airflow DAG at `dags/automated_retraining_dag.py`
* Retraining schedule changed from daily to weekly (`0 2 * * 0`)

**v2.0.0**

January 2026

## New Features

* **Kedro pipeline framework** — Reproducible, modular ML pipelines
* **Airflow orchestration** — DAG-based automation for training and monitoring
* **MLflow experiment tracking** — Full model registry with versioning and aliases
* **MinIO object storage** — S3-compatible storage for all artifacts
* **Docker Compose stack** — 20-service infrastructure with health checks

## Infrastructure

* PostgreSQL backend for Airflow + Optuna metadata
* Prometheus + Grafana monitoring with custom dashboards
* Nginx reverse proxy with SSL-ready configuration
* ClearML integration for experiment management

**v1.0.0**

December 2025

## Initial Release

* CatBoost regression model for bike-sharing demand forecasting
* FastAPI inference server with single `/predict` endpoint
* Basic train/test split for model evaluation
* CSV-based data pipeline


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.