AI image created on MidJourney V6.1 by the author.

AutoStationarity 📈

Want to Decrease Your Model’s Prediction Errors by 20%? Follow This Simple Trick

Time series modeling can be tricky, even for experienced data scientists. You’ve done everything by the book: used state-of-the-art deep learning models, performed feature engineering, normalized your data, and optimized hyperparameters. Yet, your model’s performance still falls short. If this is your case, this code may help you.

Learn why making your time series stationary improves your model accuracy. Also, discover how to automatically apply this technique in your machine learning pipeline using a simple Python script.

Usage

It is recommended to read this article for a good understanding of how to use the code and make your data stationary automatically.

1. Run pip install -r requirements.txt to install the requirements
2. Execute the code with python -m trainer

Liked this repo? Show your support!

⭐ Give the project a star
🤝 Send me a LinkedIn connection request to stay in touch

Happy reading and automation!