Self Optimizing ML Pipeline with Automated Redeployment

Student Name

Muhammad Mohsin AslamFollow

Degree

Master of Science in Computer Science

Department

Department of Computer Science

School

School of Mathematics and Computer Science (SMCS)

Date of Submission

Spring 2024

Supervisor

Dr. Tariq Mahmood, Professor and Program Coordinator MS(CS) and MS(DS) Programs, School of Mathematics and Computer Science (SMCS)

Keywords

Machine Learning Lifecycle, Machine Learning Pipelines, ETL, MLOPs, Data Science

Abstract

This project tackles the challenge of efficiently managing the lifecycle of machine learning models in production environments, where traditional methods often struggle with model updating inefficiencies, scalability issues, and inadequate performance tracking. By leveraging advanced technologies, the project develops a scalable, self-optimizing machine learning pipeline that minimizes manual intervention, reduces deployment times, and ensures models adapt over time to maintain accuracy and relevance. The proposed solution addresses the critical issue of model accuracy degradation due to evolving data trends, providing a robust framework for continuous, automated updates and integration. This approach not only enhances operational efficiency and decision-making capabilities but also sets a new standard in machine learning operations, making it possible for organizations to stay ahead in rapidly changing environments.

Keywords:

Machine Learning Lifecycle, Machine Learning Pipelines, ETL, MLOPs

Document Type

Restricted Access

Submission Type

Research Project

Recommended Citation

Aslam, Muhammad M.. "Self Optimizing ML Pipeline with Automated Redeployment." Unpublished graduate research project. Institute of Business Administration. 2024. https://ir.iba.edu.pk/research-projects-mscs/45