Praveen, Sruthi (2023) Cloud-Optimized Fusion of Time Series and Machine Learning Models for Enhanced Real-Time Forecasting. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
This study assesses the effectiveness of Time-series based Machine Learning models in forecasting product sales using stock prices of major technology companies such as Google, Amazon, Microsoft, and Apple, as well as standard datasets including air passengers’ data, shampoo sales, Big Mart sales, and a real-time dataset comprising 100 Stock Keeping Units (SKU’s). Models tested include Linear Regression, Support Vector Machine, Decision Tree, Gradient Boosting Regression, and ARIMA. The system is designed for automated data processing and preparation to ensure data integrity. Mean Squared Error, Mean Absolute Error, and Mean Absolute Percentage Error are employed for model accuracy assessment. The findings guide businesses in selecting the optimal model for predicting product commercial future, contributing to informed decisions. The research introduces a novel approach merging clustering with model selection, enhancing time series forecasting precision. Cloud platform deployment enhances accessibility and usability. This approach not only improves accuracy but also yields interpretable forecasts, benefiting various domains seeking accurate and timely predictions.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Kazmi, Aqeel UNSPECIFIED |
Subjects: | H Social Sciences > HF Commerce Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
Divisions: | School of Computing > Master of Science in Cloud Computing |
Depositing User: | Tamara Malone |
Date Deposited: | 18 Oct 2024 15:54 |
Last Modified: | 18 Oct 2024 15:54 |
URI: | https://norma.ncirl.ie/id/eprint/7101 |
Actions (login required)
View Item |