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

Asset-specific factors are commonly used to forecast financial returns andquantify asset-specific risk premia. Using various machine learning models, wedemonstrate that the information contained in these factors leads to evenlarger economic gains in terms of forecasts of sector returns and themeasurement of sector-specific risk premia. To capitalize on the strongpredictive results of individual models for the performance of differentsectors, we develop a novel online ensemble algorithm that learns to optimizepredictive performance. The algorithm continuously adapts over time todetermine the optimal combination of individual models by solely analyzingtheir most recent prediction performance. This makes it particularly suited fortime series problems, rolling window backtesting procedures, and systems ofpotentially black-box models. We derive the optimal gain function, express thecorresponding regret bounds in terms of the out-of-sample R-squared measure,and derive optimal learning rate for the algorithm. Empirically, the newensemble outperforms both individual machine learning models and their simpleaverages in providing better measurements of sector risk premia. Moreover, itallows for performance attribution of different factors across various sectors,without conditioning on a specific model. Finally, by utilizing monthlypredictions from our ensemble, we develop a sector rotation strategy thatsignificantly outperforms the market. The strategy remains robust againstvarious financial factors, periods of financial distress, and conservativetransaction costs. Notably, the strategy's efficacy persists over time,exhibiting consistent improvement throughout an extended backtesting period andyielding substantial profits during the economic turbulence of the COVID-19pandemic.

Online Ensemble of Models for Optimal Predictive Performance with Applications to Sector Rotation Strategy