A Data Mining Service for Non-Programmers

Authors

Abstract

With the emergence of Big Data, the scarcity of data scientists to analyse all the data being produced in different domains became evident. To train new data scientists faster, web applications providing data science practices without requiring programming skills can be a great help. However, some available web applications lack in providing good data mining practices, specially for assessment and selection of models. Thus, in this paper we describe a system, currently under development, that will provide the construction of data mining processes enforcing good data mining practices. The system will be available through a web UI and will follow a microservices architecture that is still being designed and tested. Preliminary usability tests, were conducted with two groups of users to evaluate the envisioned concept for the creation of data mining processes. In these tests we observed a general high level of user satisfaction. To assess the performance of the current system design, we have done tests in a public cloud where we observed interesting results that will guide us in new directions.

Subject

Data science, machine learning

Related Project

DataScience4NP: Data Science for Non-Programmers

Conference

10th International Conference on Knowledge Discovery and Information Retrieval – KDIR 2018, September 2018

PDF File

DOI