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

Factor strategies have gained growing popularity in industry with the fastdevelopment of machine learning. Usually, multi-factors are fed to an algorithmfor some cross-sectional return predictions, which are further used toconstruct a long-short portfolio. Instead of predicting the value of the stockreturn, emerging studies predict a ranked stock list using the maturelearn-to-rank technology. In this study, we propose a new listwiselearn-to-rank loss function which aims to emphasize both the top and the bottomof a rank list. Our loss function, motivated by the long-short strategy, isendogenously shift-invariant and can be viewed as a direct generalization ofListMLE. Under different transformation functions, our loss can lead toconsistency with binary classification loss or permutation level 0-1 loss. Aprobabilistic explanation for our model is also given as a generalizedPlackett-Luce model. Based on a dataset of 68 factors in China A-share marketfrom 2006 to 2019, our empirical study has demonstrated the strength of ourmethod which achieves an out-of-sample annual return of 38% with the Sharperatio being 2.

Constructing long-short stock portfolio with a new listwise learn-to-rank algorithm