Skip to content
All library documents

Profit-Oriented LSTM Forecasting for Stock Index Trading

Article arXiv papers · Author: Chariton Chalvatzis et al.
Read the original

Summary

The document describes a deep LSTM model and a trading strategy for four US stock indices. Rather than trading solely on whether the model predicts an increase or decrease, the strategy uses each predicted return’s position within the distribution of predictions to estimate trade profitability. The model is tuned for the strategy’s trading objective, highlighting that forecast quality and trading rules need to be considered together.

Reported tests cover the S&P 500, DJIA, NASDAQ, and Russell 2000 from 2010 to 2018. The document gives cumulative returns for each index and says they exceeded buy-and-hold and other recent approaches. It does not provide details here on transaction costs, risk-adjusted performance, validation design, or whether results generalize beyond that period. The reported returns should therefore be read as study results, not as evidence of future performance.

Key ideas

  • Model and trading strategy performance are linked, so they should be designed together.
  • The LSTM predicts asset prices from a modest history of trading-day observations.
  • The strategy uses predicted returns’ positions within their distribution rather than only their direction.
  • The reported evaluation covers four US stock indices over 2010–2018.

Tags

EquitiesMachine learningUS marketsBacktesting
Full text
# High-performance stock index trading: making effective use of a deep LSTM neural network


# High-performance stock index trading: making effective use of a deep LSTM neural network









We present a deep long short-term memory (LSTM)-based neural network for predicting asset prices, together with a successful trading strategy for generating profits based on the model's predictions. Our work is motivated by the fact that the effectiveness of any prediction model is inherently coupled to the trading strategy it is used with, and vise versa. This highlights the difficulty in developing models and strategies which are jointly optimal, but also points to avenues of investigation which are broader than prevailing approaches. Our LSTM model is structurally simple and generates predictions based on price observations over a modest number of past trading days. The model's architecture is tuned to promote profitability, as opposed to accuracy, under a strategy that does not trade simply based on whether the price is predicted to rise or fall, but rather takes advantage of the distribution of predicted returns, and the fact that a prediction's position within that distribution carries useful information about the expected profitability of a trade. The proposed model and trading strategy were tested on the S&P 500, Dow Jones Industrial Average (DJIA), NASDAQ and Russel 2000 stock indices, and achieved cumulative returns of 340%, 185%, 371% and 360%, respectively, over 2010-2018, far outperforming the benchmark buy-and-hold strategy as well as other recent efforts.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.