Layman Analytics System: A Cloud-Enabled System for Data Analytics Workflow Recommendation

Theint Theint Aye

doi:10.1109/TASE.2016.2610521

Layman Analytics System: A Cloud-Enabled System for Data Analytics Workflow Recommendation

2017-01-01

5

PRE

AI

DOI：10.1109/TASE.2016.2610521

Original

Original request for help

Save

Abstract

En 中文

In today's big data era, there is a tremendously huge amount of data available. Layman users lack not only the knowledge and experience in data analytics to make sense of these data but also the computational resources for executing the analytics. In this paper, we propose and develop a layman analytics system (LAS), which provides the layman users with a scalable and ready-to-use analytics tool to automatically generate analytics workflows for classification tasks. The LAS is designed to benefit from existing open-source data analytics tools using generic ontological modeling of analytics operators from these tools as well as adaptive constraint refinement for metadata learning. Moreover, the LAS can be deployed on both public and private clouds to cater to the need of scalable computing and easy maintenance. To demonstrate the performance of the LAS, we conducted experiments with 114 data sets obtained from the University of California Irvine Machine Learning Repository. The workflows generated by the LAS were benchmarked against the OpenML whereby each data set has a range of classification accuracy obtained using classifiers designed and fine-tuned by data experts. The comparisons showed that 87 out of 114 data sets have exceeded the 50th percentile of the benchmark data. Among these 87 data sets, the LAS outperforms the 90th percentile of the benchmarks on 49 data sets. Note to Practitioners-The era of the Internet of Things demands effective means to analyze a huge amount of available data in order to extract meaningful insight. This task has been limited to data scientists due to its intricate nature and steep learning curve. To empower the layman, we propose a system that automatically generates recommended workflows for classification tasks and performs remote and parallel execution of the workflow in a cloud computing environment efficiently. Our system receives an input data set from the user and extracts its unique features. This is compared with a repository of data set-workflow pairs to select appropriate workflows. These workflows are intelligently aggregated into a better performing version using an evolutionary algorithm. Upon completion of the classification task, users can choose to contribute the results back into the repository, which could improve subsequent system performance. The approach described is fully automatic and requires no user intervention. This makes it an ideal tool for layman users. To ascertain that the system performs sufficiently well, we tested it on 114 data sets from the UCI Machine Learning Repository and compared the classification accuracies of our recommended workflows with those of the single classifiers in the OpenML. The results showed that our system is able to generate workflows with accuracies that are among the top-ranked classifiers in the OpenML and sometimes even better.

Keywords:

Cloud infrastructure

generic ontological modeling

layman analytics system (LAS)

workflow recommender

Layman Analytics System: A Cloud-Enabled System for Data Analytics Workflow Recommendation

Abstract

AI Summary

Journal

Organization

Cited Papers