Research Article
Introducing the BrewAI AutoML Tool
@INPROCEEDINGS{10.1007/978-3-030-95987-6_14, author={Siu Lung Ng and Fethi A. Rabhi and Gavin Whyte and Andy Zeng}, title={Introducing the BrewAI AutoML Tool}, proceedings={IoT as a Service. 7th EAI International Conference, IoTaaS 2021, Sydney, Australia, December 13--14, 2021, Proceedings}, proceedings_a={IOTAAS}, year={2022}, month={7}, keywords={AutoML Web application ML pipeline ML for business}, doi={10.1007/978-3-030-95987-6_14} }- Siu Lung Ng
Fethi A. Rabhi
Gavin Whyte
Andy Zeng
Year: 2022
Introducing the BrewAI AutoML Tool
IOTAAS
Springer
DOI: 10.1007/978-3-030-95987-6_14
Abstract
AutoML tools provide an automation service for data scientists and software engineers to save time from data preprocessing and modeling building. Existing AutoML tools usually require users to have data science knowledge and programming skills to use the services, however, most non-expert and business users do not have such skills to use these AutoML tools. In addition, many AutoML tools require a special infrastructure or cloud provider. In this paper, we introduce BrewAI: a commercial-grade tool that provides an easy-to-use AutoML service for business users. The paper describes how the use of service-oriented computing design principles gives BrewAI flexibility, scalability and performance at a reasonable cost. The paper also describes a case study that shows how BrewAI enables business users to outperform more than three-quarters of Kaggle competitors in an NLP classification task.
