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 report successful results from using deep learning neural networks (DLNNs)to learn, purely by observation, the behavior of profitable traders in anelectronic market closely modelled on the limit-order-book (LOB) marketmechanisms that are commonly found in the real-world global financial marketsfor equities (stocks & shares), currencies, bonds, commodities, andderivatives. Successful real human traders, and advanced automated algorithmictrading systems, learn from experience and adapt over time as market conditionschange; our DLNN learns to copy this adaptive trading behavior. A novel aspectof our work is that we do not involve the conventional approach of attemptingto predict time-series of prices of tradeable securities. Instead, we collectlarge volumes of training data by observing only the quotes issued by asuccessful sales-trader in the market, details of the orders that trader isexecuting, and the data available on the LOB (as would usually be provided by acentralized exchange) over the period that the trader is active. In this paperwe demonstrate that suitably configured DLNNs can learn to replicate thetrading behavior of a successful adaptive automated trader, an algorithmicsystem previously demonstrated to outperform human traders. We also demonstratethat DLNNs can learn to perform better (i.e., more profitably) than the traderthat provided the training data. We believe that this is the first everdemonstration that DLNNs can successfully replicate a human-like, orsuper-human, adaptive trader operating in a realistic emulation of a real-worldfinancial market. Our results can be considered as proof-of-concept that a DLNNcould, in principle, observe the actions of a human trader in a real financialmarket and over time learn to trade equally as well as that human trader, andpossibly better.

Deep Learning can Replicate Adaptive Traders in a Limit-Order-Book Financial Market