ISSN :2582-9793

NoxTrader: LSTM-Based Stock Return Momentum Prediction for Quantitative Trading

Original Research (Published On: 01-Dec-2023 )
NoxTrader: LSTM-Based Stock Return Momentum Prediction for Quantitative Trading
DOI : https://dx.doi.org/10.54364/AAIML.2023.1195

Hsiang-Hui Liu, Han-Jay Shu and Wei-Ning Chiu

Adv. Artif. Intell. Mach. Learn., 3 (4):1670-1680

Hsiang-Hui Liu : Department of Computer Science of National Tsing-Hua University

Han-Jay Shu : Department of Electrical Engineering and Computer Science of National Tsing-Hua University

Wei-Ning Chiu : Department of Computer Science of National Tsing-Hua University

Download PDF Here

DOI: https://dx.doi.org/10.54364/AAIML.2023.1195

Article History: Received on: 31-Oct-23, Accepted on: 23-Nov-23, Published on: 01-Dec-23

Corresponding Author: Hsiang-Hui Liu

Email: morrisliuting@gmail.com

Citation: Hsiang-Hui Liu , Han-Jay Shu, Wei-Ning Chiu (2023). NoxTrader: LSTM-Based Stock Return Momentum Prediction for Quantitative Trading. Adv. Artif. Intell. Mach. Learn., 3 (4 ):1670-1680


Abstract

    

We introduce NoxTrader, a sophisticated system designed for portfolio construction and trading execution with the primary objective of achieving profitable outcomes in the stock market, specifically aiming to generate moderate to long-term profits. The underlying learning process of NoxTrader is rooted in the assimilation of valuable insights derived from historical trading data, particularly focusing on time-series analysis due to the nature of the dataset employed. In our approach, we utilize price and volume data of US stock market for feature engineering to generate effective features, including Return Momentum, Week Price Momentum, and Month Price Momentum. We choose the Long Short-Term Memory (LSTM) model to capture continuous price trends and implement dynamic model updates during the trading execution process, enabling the model to continuously adapt to the current market trends. Notably, we have developed a comprehensive trading backtesting system — NoxTrader, which allows us to manage portfolios based on predictive scores and utilize custom evaluation metrics to conduct a thorough assessment of our trading performance. Our rigorous feature engineering and careful selection of prediction targets enable us to generate prediction data with an impressive correlation range between 0.65 and 0.75. Finally, we monitor the dispersion of our prediction data and perform a comparative analysis against actual market data. Through the use of filtering techniques, we improved the initial -60% investment return to 325%

Statistics

   Article View: 290
   PDF Downloaded: 16