English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We employ both random forests and LSTM networks (more precisely CuDNNLSTM) astraining methodologies to analyze their effectiveness in forecastingout-of-sample directional movements of constituent stocks of the S&P 500 fromJanuary 1993 till December 2018 for intraday trading. We introduce amulti-feature setting consisting not only of the returns with respect to theclosing prices, but also with respect to the opening prices and intradayreturns. As trading strategy, we use Krauss et al. (2017) and Fischer & Krauss(2018) as benchmark. On each trading day, we buy the 10 stocks with the highestprobability and sell short the 10 stocks with the lowest probability tooutperform the market in terms of intraday returns -- all with equal monetaryweight. Our empirical results show that the multi-feature setting provides adaily return, prior to transaction costs, of 0.64% using LSTM networks, and0.54% using random forests. Hence we outperform the single-feature setting inFischer & Krauss (2018) and Krauss et al. (2017) consisting only of the dailyreturns with respect to the closing prices, having corresponding daily returnsof 0.41% and of 0.39% with respect to LSTM and random forests, respectively.

Forecasting directional movements of stock prices for intraday trading using LSTM and random forests