Stock Market prediction on High frequency data using Long-Short Term Memory

摘要

High Frequency Trading (HFT) is part of algorithmic trading, and one of the biggest changes that happened in the last 15 years. HFT or nanotrading represents the ability, for a trader, to take orders within very short delays. This paper presents a model based on technical indicators with Long Short Term Memory in order to forecast the price of a stock one-minute, five-minutes and ten-minutes ahead. First, we get the S&P500 intraday trading data from Kaggle, then we calculate technical indicators and finally, we train the regression Long-Short Term Memory model. Based on the price history, alongside technical analysis indicators and strategies, this model is executed, and the results are analyzed based on performance metrics and profitability. Experiment results show that the proposed method is effective as well as suitable for prediction a few minutes before.