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

The article is concerned with the problem of multi-step financial time seriesforecasting of Foreign Exchange (FX) rates. To address this problem, weintroduce a regression network termed RegPred Net. The exchange rate toforecast is treated as a stochastic process. It is assumed to follow ageneralization of Brownian motion and the mean-reverting process referred to asthe generalized Ornstein-Uhlenbeck (OU) process, with time-dependentcoefficients. Using past observed values of the input time series, thesecoefficients can be regressed online by the cells of the first half of thenetwork (Reg). The regressed coefficients depend only on - but are verysensitive to - a small number of hyperparameters required to be set by a globaloptimization procedure for which, Bayesian optimization is an adequateheuristic. Thanks to its multi-layered architecture, the second half of theregression network (Pred) can project time-dependent values for the OU processcoefficients and generate realistic trajectories of the time series.Predictions can be easily derived in the form of expected values estimated byaveraging values obtained by Monte Carlo simulation. The forecasting accuracyon a 100 days horizon is evaluated for several of the most important FX ratessuch as EUR/USD, EUR/CNY, and EUR/GBP. Our experimental results show that theRegPred Net significantly outperforms ARMA, ARIMA, LSTMs, and Autoencoder-LSTMmodels in terms of metrics measuring the absolute error (RMSE) and correlationbetween predicted and actual values (Pearson R, R-squared, MDA). Compared toblack-box deep learning models such as LSTM, RegPred Net has betterinterpretability, simpler structure, and fewer parameters.

Forecasting foreign exchange rates with regression networks tuned by Bayesian optimization