Authors : Aishwarya Umare, Akanksha Deshmukh, Harsh Kalbande, Lalit Bhanarkar, Prof. Riddhi Doshi
DOI : 10.46335/IJIES.2024.9.7.14
Article Link
Abstract— This paper presents a comprehensive approach to designing an end-to-end reusable data analytics pipeline using machine learning (ML) concepts. The proposed pipeline combines different machine learning techniques, such as data preprocessing, feature engineering, model training, and evaluation, to automate the data analysis and decision-making process. The pipeline is designed to be modular, scalable, and reusable, allowing organizations to efficiently analyze and derive insights from their data. Additionally, the paper discusses the challenges and considerations in implementing the pipeline, such as data quality, scalability, and interpretability. The suggested pipeline is assessed utilizing real-world datasets, showcasing its effectiveness in enhancing the efficiency and accuracy of data analytics tasks.
