TradeX

Screenshots

Problem Statement

The agent is designed to facilitate trading on the ETH/USDC pool using an AI-driven strategy. The goal is to optimize trades based on market conditions, leveraging machine learning models for prediction and decision-making. In this project, we are using a simple multi-layer perceptron to predict the next day's prices. After training the model, we need to compile it into the ONNX format, which will be used in the next step to transpile it into Cairo.

Solution

Tech StackGiza CLI & SDK: For model training, ONNX conversion, cairo transpilation and deployment.Starknet Mainnet: Blockchain platform for deploying and executing contracts.PyTorch: Framework for building deep learning models.Python Libraries: Poetry for Python dependencies,Pandas, numpy, yFinance for historical data, scikit-learn for ML tooling.