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

Stock trend forecasting is a fundamental task of quantitative investmentwhere precise predictions of price trends are indispensable. As an onlineservice, stock data continuously arrive over time. It is practical andefficient to incrementally update the forecast model with the latest data whichmay reveal some new patterns recurring in the future stock market. However,incremental learning for stock trend forecasting still remains under-exploreddue to the challenge of distribution shifts (a.k.a. concept drifts). With thestock market dynamically evolving, the distribution of future data can slightlyor significantly differ from incremental data, hindering the effectiveness ofincremental updates. To address this challenge, we propose DoubleAdapt, anend-to-end framework with two adapters, which can effectively adapt the dataand the model to mitigate the effects of distribution shifts. Our key insightis to automatically learn how to adapt stock data into a locally stationarydistribution in favor of profitable updates. Complemented by data adaptation,we can confidently adapt the model parameters under mitigated distributionshifts. We cast each incremental learning task as a meta-learning task andautomatically optimize the adapters for desirable data adaptation and parameterinitialization. Experiments on real-world stock datasets demonstrate thatDoubleAdapt achieves state-of-the-art predictive performance and showsconsiderable efficiency.

DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting