Litcius/Paper detail

Automating the Machine Learning Process using PyCaret and Streamlit

Nikhilesh Sarangpure, Vipul Dhamde, Ankita Roge, Janhawi Doye, Shivam Patle, Sukhad Tamboli

202330 citationsDOI

Abstract

Machine learning applications for the industry have seen significant growth and attention in recent years. As a result, there is a significant need for Machine learning engineers across the business, but increasing their productivity is still a major problem. For time-consuming Machine learning pipeline operations such as data pre-processing, feature engineering, model selection, hyperparameter optimization, and prediction result analysis, Automated Machine Learning (AutoML) has arisen as a solution. In this research, we examine the condition of the AutoML application, which aims to automate ML operations. We do multiple evaluations based on numerous datasets, in various data segments, to assess their functionality and compare the outcomes. Using Streamlit, the AutoML application is made to provide a user interface.

Topics & Concepts

Machine learningComputer scienceArtificial intelligencePipeline (software)HyperparameterProcess (computing)Feature engineeringSelection (genetic algorithm)Feature selectionFeature (linguistics)Deep learningLinguisticsPhilosophyOperating systemProgramming languageMachine Learning and Data ClassificationData Stream Mining TechniquesBig Data and Business Intelligence
Automating the Machine Learning Process using PyCaret and Streamlit | Litcius