Beating the S&amp;amp;P 500 index &amp;#x2014; A successful neural network approach

Sethi, Mininder; Treleaven, Philip; Rollin, Sebastian del Baño

doi:10.1109/ijcnn.2014.6889625

Cited by 4 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some others [11] apply the LSTM combined with autoencoders to analyze stock price series in order to predict future prices. Besides predicting the price itself, there are also studies [12] [13] [14] building neural networks to predict the future direction of stock prices and aims to achieve high classification accuracy.…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data

Zhao

2020

Preprint

View full text Add to dashboard Cite

This paper presents a deep learning framework based on Long Short-term Memory Network(LSTM) that predicts price movement of cryptocurrencies based on a trailing window. It is the first to use trade-by-trade data to predict shortterm price changes in fixed time horizons. By carefully designing features and detailed searching for best hyper-parameters, the model is trained to achieve high performance on nearly a year of trade-by-trade data. The optimal model delivers stable high performance(over 60% accurancy) on out-of-sample test periods. In a realistic trading simulation setting, the prediction made by the model could be easily monetized. Moreover, this study shows that the LSTM model could extract universal features from tradeby-trade data, as the learned parameters well maintain their high performance on other cryptocurrency instruments that were not included in training data. This study exceeds existing researches in term of the scale and precision of data used, as well as the high prediction accuracy achieved.

show abstract

Section: Related Workmentioning

confidence: 99%

A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data

Zhao

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…diction model is "consistent" with the trading strategy, e.g., the model predicts the direction of the price movement -but not the numerical value of the price -which is then used with a directional trading strategy. Sethi et al (2014) presented a neural network which used only two features to predict the direction (up or down) of next-day price movement for the largest 100 stocks (in terms of market capitalization) in the S&P 500 index. Those stocks were then combined into a portfolio in order to "beat" the index itself.…”

Section: Literature Reviewmentioning

confidence: 99%

“…One of the open questions has been whether (and how) one can forecast the behavior of stocks and then act accordingly to generate "excess returns", i.e., profit in excess of those generated by the market itself (Fama and French, 1993). Towards that end, significant effort has been put into predicting the price of major U.S. stock indices such as the S&P 500 or the Dow Jones Industrial Average (DJIA) (Huck, 2009(Huck, , 2010Sethi et al, 2014;Krauss et al, 2017;Bao et al, 2017) as well as that of individual stocks, using techniques ranging from early linear models (Fama and French, 2004) to machine learning and neural network-based approaches (Sermpinis et al, 2013;Deng et al, 2017;Minh et al, 2018). There are two components which are generally part of the overall discussion on "intelligent" or automatic trading: a predictive model whose purpose is to anticipate an asset's future price, and a trading strategy which uses the model's predictions to generate profit.…”

Section: Introductionmentioning

confidence: 99%

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

Chalvatzis¹,

Hristu-Varsakelis²

2019

Preprint

View full text Add to dashboard Cite

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.

show abstract

“…For the past decade, deep neural networks have exhibited very good performance in many different fields such as computer vision, natural language processing and robotics. In recent years, it has been shown that deep learning is capable of identifying nonlinearities in time series data leading to profitable strategies [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Augmenting Transferred Representations for Stock Classification

Fons

Dawson²,

Zeng

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Stock classification is a challenging task due to high levels of noise and volatility of stocks returns. In this paper we show that using transfer learning can help with this task, by pre-training a model to extract universal features on the full universe of stocks of the S&P500 index and then transferring it to another model to directly learn a trading rule. Transferred models present more than double the risk-adjusted returns than their counterparts trained from zero.In addition, we propose the use of data augmentation on the feature space defined as the output of a pre-trained model (i.e. augmenting the aggregated time-series representation). We compare this augmentation approach with the standard one, i.e. augmenting the timeseries in the input space. We show that augmentation methods on the feature space leads to 20% increase in risk-adjusted return compared to a model trained with transfer learning but without augmentation.

show abstract

Beating the S&P 500 index — A successful neural network approach

Cited by 4 publications

References 8 publications

A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data

A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data

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

Augmenting Transferred Representations for Stock Classification

Contact Info

Product

Resources

About