How to Fine-tune Time Series Forecasting Models for Crypto Coins

Author(s): Eivind Kjosbakken

Originally published on Towards AI.

Predict the Future Value of Crypto Coins with Fine-tuned Time Series Forecasting Models

This member-only story is on us. Upgrade to access all of Medium.

In this article, I will show you how you can use time series forecasting to predict the future price of a cryptocurrency coin. I will then move into the more advanced topic of fine-tuning the forecasting model for a specific coin in order to improve prediction quality.

Predict future cryptocurrency prices using fine-tuned time series forecasting models. Image by ChatGPT.

· Downloading data· Making the training and evaluation dataset· Setting up Chronos time-series forecasting model· Evaluate the base Chronos model· Fine-tune Chronos model· Evaluate fine-tuned model· Conclusion

Note that the contents of this article are not financial advice, and you should use the code at your own risk.

If you want to keep it simple, you can download this Bitcoin dataset online, which I will use for the rest of the article. If you use this data, you can jump directly to the next section. However, if you want to download your own data, you can follow the steps below.

I will be downloading data for the AAVE coin. This is a smaller coin, and I was not able to find a quality dataset online. I, therefore, downloaded my own dataset with the CCXT… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI