AI Models for Time Series Analysis? Testing LLM’s for Crypto Price Prediction

This video tests whether Large Language Models (LLM's) are effective at predicting time series data in comparison to traditional methods such as ARIMA. I use time series data from the crypto market, including Bitcoin (BTC), Ethereum (ETH), and Ripple (XRP), in addition to three different LLM models: Meta Llama 3, Google Gemma 2, and Mistral 7B. This analysis was done using Python and the replication code can be found below.

If LLM's have the capacity to predict time series, then it unlocks a whole new area of quantitative financial modeling. Otherwise, it is just hype.

***Important Note: This video is not financial or investing advice. It is an educational tutorial on how to use AI models with financial time series data.**

Like, Comment, and Subscribe to the Deep Charts Channel for more informative AI, Machine Learning, and Financial Markets tutorials.

*Data Science Resources*
Replication code here: https://github.com/deepcharts/projects