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

E-commerce business is revolutionizing our shopping experiences by providingconvenient and straightforward services. One of the most fundamental problemsis how to balance the demand and supply in market segments to build anefficient platform. While conventional machine learning models have achievedgreat success on data-sufficient segments, it may fail in a large-portion ofsegments in E-commerce platforms, where there are not sufficient records tolearn well-trained models. In this paper, we tackle this problem in the contextof market segment demand prediction. The goal is to facilitate the learningprocess in the target segments by leveraging the learned knowledge fromdata-sufficient source segments. Specifically, we propose a novel algorithm,RMLDP, to incorporate a multi-pattern fusion network (MPFN) with ameta-learning paradigm. The multi-pattern fusion network considers both localand seasonal temporal patterns for segment demand prediction. In themeta-learning paradigm, transferable knowledge is regarded as the modelparameter initialization of MPFN, which are learned from diverse sourcesegments. Furthermore, we capture the segment relations by combiningdata-driven segment representation and segment knowledge graph representationand tailor the segment-specific relations to customize transferable modelparameter initialization. Thus, even with limited data, the target segment canquickly find the most relevant transferred knowledge and adapt to the optimalparameters. We conduct extensive experiments on two large-scale industrialdatasets. The results justify that our RMLDP outperforms a set ofstate-of-the-art baselines. Besides, RMLDP has been deployed in Taobao, areal-world E-commerce platform. The online A/B testing results furtherdemonstrate the practicality of RMLDP.

Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records