Skip to content
#

cfm

Here are 18 public repositories matching this topic...

This project classifies stocks based on tick-by-tick order-book data, as part of the CFM challenge. The model uses GRU layers to process sequential market data and leverages feature engineering on prices, bid/ask sizes, and order types. It’s trained with cross-entropy loss using the Adam optimizer.

  • Updated Oct 28, 2024
  • Jupyter Notebook

Add this topic to your repo

To associate your repository with the cfm topic, visit your repo's landing page and select "manage topics."

Learn more