Skip to content

Antonio-IF/MicroTrading

Repository files navigation

MICROSTRUCTURE AND TRADING SYSTEMS - Summer 2024

Understanding the microstructure of financial markets and mastering trading systems is essential for anyone looking to succeed in the fast-paced world of finance. Key aspects such as market microstructure, algorithmic trading, and quantitative analysis, leveraging techniques from technical analysis to advanced Deep Learning models, are crucial.

Through this projects, we will gain the skills to make informed decisions and navigate the complexities of modern trading systems, enhancing our ability to operate effectively in financial markets.

Projects

In this course, we will work on four distinct projects. These projects are designed to enhance our skills in making informed decisions and navigating the complexities of modern trading systems.

1. Microstructure

This project explores market microstructure concepts, focusing on bid-ask spreads and market maker profitability. Inspired by Bagehot's insights and Copeland & Galai's model, we aim to implement these theories practically.

We will simulate stock price movements and introduce a probability factor for informed trades. Deliverables include plotting price distributions, calculating expected revenue under different trade scenarios, and determining optimal bid and ask prices based on Copeland & Galai's model.

2. Technical Analysis

Technical analysis is a fundamental tool for trading, as it provides valuable information on market trends, support and resistance levels, pattern recognition, risk management, and entry and exit timing.

Traders who use technical analysis look at historical price data and use various tools and indicators to identify patterns and trends. These patterns can indicate the future direction of an asset's price, which can help traders make informed decisions about when to buy or sell.

3. Classification

In this project we focus on the implementation and optimization of classification models to predict buy and sell signals in the stock and cryptocurrency markets. We employ a combination of machine learning algorithms, including Logistic Regression, Support Vector Classification (SVC), and XGBoost, integrated into a voting classifier to enhance the accuracy of our predictions. We utilize the optuna library for hyperparameter optimization, further improving the performance of our models. The ultimate goal is to provide an effective tool for anticipating market movements and maximizing expected returns in financial operations.

4. Fixing Transformer

Continuous monitoring, frequent retraining, and strategic capital management are crucial for maintaining an effective trading model. While challenges persist, the insights gained provide a pathway for ongoing refinement and improved performance in dynamic financial markets.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published