Document Type
Dissertation
Date of Award
12-31-2024
Degree Name
Doctor of Philosophy in Data Science - (Ph.D.)
Department
Data Science
First Advisor
Chase Qishi Wu
Second Advisor
Guiling Wang
Third Advisor
David A. Bader
Fourth Advisor
Ioannis Koutis
Fifth Advisor
Duan Qiang
Abstract
Machine learning and AI techniques are transforming supply chain forecasting, driven by the expanding availability of data assets. These advanced methods offer powerful opportunities to optimize management processes, reduce operational costs, and enhance strategic decision-making, which is crucial for enterprise success. However, conventional statistical approaches, such as Autoregressive Integrated Moving Average Models (ARIMA), dynamic regression, and Unobserved Component Models (UCMs)—which have long dominated time series forecasting—often fall short in accuracy and scalability. These traditional models face limitations in batch processing, handling large-scale data, addressing uncertainty-induced disruptions, and synchronizing demand-supply scenarios.
To address these challenges, a novel class of AI-powered ensemble techniques is introduced, integrating machine learning, particularly neural network, with baseline models. The approach starts with classification and segmentation, applying feature engineering to signal components such as spikes and anomalies, which are treated as outliers, to capture complex scenario hierarchies and identify patterns in categorical data. Next, an ensemble model incorporating AI-driven time-series pattern sensors automatically detects critical signal elements, including seasonality, promotions, trends, and intermittent or discontinued activities. An evaluation of eight widely used model categories shows that this AI-enhanced ensemble approach significantly outperforms individual baseline models and traditional univariate time-series algorithms in forecasting accuracy.
Recommended Citation
Zhang, Minjuan, "Ensemble learning models for large-scale time series forecasting in supply chain" (2024). Dissertations. 1813.
https://digitalcommons.njit.edu/dissertations/1813
