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

In the industry of video content providers such as VOD and IPTV, predictingthe popularity of video contents in advance is critical not only from amarketing perspective but also from a network optimization perspective. Bypredicting whether the content will be successful or not in advance, thecontent file, which is large, is efficiently deployed in the proper serviceproviding server, leading to network cost optimization. Many previous studieshave done view count prediction research to do this. However, the studies havebeen making predictions based on historical view count data from users. In thiscase, the contents had been published to the users and already deployed on aservice server. These approaches make possible to efficiently deploy a contentalready published but are impossible to use for a content that is not bepublished. To address the problems, this research proposes a hybrid machinelearning approach to the classification model for the popularity prediction ofnewly video contents which is not published. In this paper, we create a newvariable based on the related content of the specific content and divide entiredataset by the characteristics of the contents. Next, the prediction isperformed using XGBoosting and deep neural net based model according to thedata characteristics of the cluster. Our model uses metadata for contents forprediction, so we use categorical embedding techniques to solve the sparsity ofcategorical variables and make them learn efficiently for the deep neural netmodel. As well, we use the FTRL-proximal algorithm to solve the problem of theview-count volatility of video content. We achieve overall better performancethan the previous standalone method with a dataset from one of the topstreaming service company.

Hybrid Machine Learning Approach to Popularity Prediction of Newly Released Contents for Online Video Streaming Service