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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The massive increase in the data volume and dataset availability for analystscompels researchers to focus on data content and select high-quality datasetsto enhance the performance of analytics operators. While selecting the highestquality data for analysis highly increases task accuracy and efficiency, it isstill a hard task, especially when the number of available inputs is verylarge. To address this issue, we propose a novel methodology that infers theoutcome of analytics operators by creating a model from datasets similar to thequeried one. Dataset similarity is performed via projecting each dataset to avector embedding representation. The vectorization process is performed usingour proposed deep learning model NumTabData2Vec, which takes a whole datasetand projects it into a lower vector embedding representation space. Throughexperimental evaluation, we compare the prediction performance and theexecution time of our framework to another state-of-the-art modelling operatorframework, illustrating that our approach predicts analytics outcomesaccurately. Furthermore, our vectorization model can project differentreal-world scenarios to a lower vector embedding representation and distinguishbetween them.

Data Analysis Prediction over Multiple Unseen Datasets: A Vector Embedding Approach