fyp23025site

Neural Network Models in

Stock Market under

Real-life Simulation

Project Introduction

This project aims to explore existing algorithmic trading strategies in literature and to build one by combining different algorithms including neural networks, mathematical and statistical models. To make it more practical, it is also expected to perform well under real-life simulation by responding to news data feeds. With our model, stock orders can be executed automatically and be more profitable.

To present the model and to provide easiness for traders, a trading simulation platform will be included, where users can input their strategies, run back tests, and view their evaluation reports.

Background

Ever since the emergence of financial trading, a wide range of trading strategies have been explored by professionals. With the tremendous changes in technology, algorithmic trading performed by automated pre-programmed trading instructions not only offered traders with alternatives of higher speed and better performance that exceed human limits, but also opened up new possibilities to advanced creations of multidisciplinary models. In particular, mathematical, statistical models as well as AI algorithms are heated topics in literature.

Machine learning has proven to be a powerful tool in quantitative trading, with itspotential to predict prices and to integrate various sources of information. By far,models recurrent neural network (RNN), convolutional neural network (CNN), and longshort-term memory (LSTM) have been implemented by researchers.

Methodology

Whether you’re looking to escape the hustle and bustle of city life, reconnect with nature, or simply indulge in a well-deserved retreat, our resort offers a unique experience that will leave you feeling refreshed and inspired.

We take pride in our commitment to sustainability, and every aspect of our resort has been designed to minimize our impact on the environment. From our use of renewable materials to our eco-friendly practices, we strive to create a sustainable and responsible oasis for our guests.