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

Pairs trading is a family of trading techniques that determine their policiesbased on monitoring the relationships between pairs of assets. A common pairstrading approach relies on describing the pair-wise relationship as a linearSpace State (SS) model with Gaussian noise. This representation facilitatesextracting financial indicators with low complexity and latency using a KalmanFilter (KF), that are then processed using classic policies such as BollingerBands (BB). However, such SS models are inherently approximated and mismatched,often degrading the revenue. In this work, we propose KalmenNet-aided Bollingerbands Pairs Trading (KBPT), a deep learning aided policy that augments theoperation of KF-aided BB trading. KBPT is designed by formulating an extendedSS model for pairs trading that approximates their relationship as holdingpartial co-integration. This SS model is utilized by a trading policy thataugments KF-BB trading with a dedicated neural network based on the KalmanNetarchitecture. The resulting KBPT is trained in a two-stage manner which firsttunes the tracking algorithm in an unsupervised manner independently of thetrading task, followed by its adaptation to track the financial indicators tomaximize revenue while approximating BB with a differentiable mapping. KBPTthus leverages data to overcome the approximated nature of the SS model,converting the KF-BB policy into a trainable model. We empirically demonstratethat our proposed KBPT systematically yields improved revenue compared withmodel-based and data-driven benchmarks over various different assets.

Neural Augmented Kalman Filtering with Bollinger Bands for Pairs Trading