Investigating the Effectiveness of Traditional VS Hybrid Time Series Models in Operational Planning.
Supervisor
Matt Lemon
Programme
MSc in Data Analytics
Subject
Computer Science
Abstract
This study conducts a systematic comparison of traditional and hybrid time series forecasting models for operational planning in a SaaS company, using large multichannel, multilanguage datasets aggregated at six-hour intervals. Classical models (ARIMA, SARIMA, ETS) are evaluated against hybrid models (ARIMA-ANN, SARIMA-ANN, ETS-ANN) to assess their ability to capture both linear and nonlinear patterns. Forecasts over a three-month horizon were evaluated using RMSE, MAE, and MAPE, with hyperparameter optimization applied to all models. Results show that hybrid models, particularly ARIMA-ANN and SARIMA-ANN, outperform traditional models in predicting volatile and high-volume data, while traditional models remain competitive for stable datasets. These findings provide insights into balancing forecasting accuracy, interpretability, and computational efficiency in operational decision-making.
Date of Award
2025
Full Publication Date
2025
Access Rights
open access
Document Type
Capstone Project
Resource Type
thesis
Recommended Citation
Priolo, C.
(2025) Investigating the Effectiveness of Traditional VS Hybrid Time Series Models in Operational Planning. CCT College Dublin.
DOI: https://doi.org/10.63227/652.299.110