Machine Learning-Based Momentum Strategy for High Frequency Trading and Buy/Sell Calls Using Algorithmic Trading

Machine Learning-Based Momentum Strategy for High Frequency Trading and Buy/Sell Calls Using Algorithmic Trading

Anupriya Dasgupta

Electronics and Telecommunications

Sardar Patel Institute of Technology

Mumbai, India anupriya.dasgupta@spit.ac.in

Oindrella Ghosh

Electronics and Telecommunications

Sardar Patel Institute of Technology

Mumbai, India oindrella.ghosh@spit.ac.in

Sanskar Laddha

Electronics and Telecommunications

Sardar Patel Institute of Technology

Mumbai, India sanskar.laddha@spit.ac.in

Milind Paraye

Electronics and Telecommunications

Sardar Patel Institute of Technology

Mumbai, India milind_paraye@spit.ac.in

Abstract — Stock Market Prediction is beneficial to investors. It provides shareholders with useful assistance in making suitable decisions about whether to purchase or sell shares. Accurate stock price prediction is extremely challenging because of multiple factors. Stock prices are influenced by a variety of factors, but the price at any given time is determined by supply and demand in the market. Due to the growing volume of data, it is now impractical, if not impossible for humans to manually analyze data for certain tasks like predicting stock market movements, necessitating automation. The stock price data represents a financial time series data which becomes more difficult to predict due to its characteristics and dynamic nature. Thus, this also means that there is a lot of data to find patterns in. This gives rise to the concept of algorithmic trading, which uses automated, pre-programmed trading strategies to execute orders. Machine learning algorithms explore large amounts of data and search for a model that will achieve the programmer’s goal. Our project’s goal is to use machine learning to implement a momentum strategy. We attempted to predict trading signals using machine learning techniques based on a set of technical indicators and rules.