AI-Driven Decision Making in Business Analytics

Authors

  • Veerendeswari J Head of the Dept, Dept. of IT, Rajiv Gandhi College of Engg. & Tech, Kirumampakkam, Puducherry, India. Author
  • Keerthana Priya M UG Scholar, Dept. of IT, Rajiv Gandhi College of Engg. & Tech, Kirumampakkam, Puducherry, India. Author
  • Shushmita P UG Scholar, Dept. of IT, Rajiv Gandhi College of Engg. & Tech, Kirumampakkam, Puducherry, India. Author
  • Varsha S S UG Scholar, Dept. of IT, Rajiv Gandhi College of Engg. & Tech, Kirumampakkam, Puducherry, India. Author

DOI:

https://doi.org/10.47392/IRJAEH.2025.0269

Keywords:

Small and medium-sized enterprises, Machine Learning automation, Hyperparameter tuning, Feature engineering, Auto ML

Abstract

Machine learning has the potential to transform industries, but many small and medium-sized enterprises (SMEs) struggle with the technical demands of building optimized models. To solve this, we propose an user-friendly framework powered by Automated Machine Learning (AutoML) tools. TPOT helps automate the complex task of choosing the right algorithms and hyperparameter tuning their settings, while PyCaret simplifies data preprocessing tasks such as feature engineering, class imbalance handling, and encoding. and allows quick testing of different models. Together, these tools make the entire machine learning process faster and more accessible even for those with limited experience. In a manufacturing case study, our approach improved prediction accuracy and cut down both time and cost. This solution supports scalable AI adoption and helps SMEs benefit from the power of intelligent automation.

Downloads

Download data is not yet available.

Downloads

Published

2025-04-28

How to Cite

AI-Driven Decision Making in Business Analytics. (2025). International Research Journal on Advanced Engineering Hub (IRJAEH), 3(04), 1857-1863. https://doi.org/10.47392/IRJAEH.2025.0269

Similar Articles

1-10 of 954

You may also start an advanced similarity search for this article.