| Summary: | Objective: This study assesses the performance of the Holt Integrated Moving Average (HIMA) model by utilizing Holt’s method and a Moving Average model. The study aims to enhance forecast accuracy by addressing shortcomings in univariate time-series predictions. Theoretical Framework: Holt’s method offers several benefits. However, it has significant limitations, such as projecting a continuous trend, either increasing or decreasing. The theoretical focus is on improving environmental monitoring through better predictive accuracy. Method: Data PM2.5 concentrations in Klang and Shah Alam, Selangor, Malaysia, from 2018 to 2020 were partitioned using Repeated Time-Series Cross Validation to test various model configurations. Results and Discussion: Results indicated that the HIMA, particularly HIMA [Holt – MA], generally performed better than Holt’s method. The study confirms the efficacy of integrating moving average adjustments into Holt’s method to improve predictions in environmental monitoring, which is crucial for effective air quality management and health-related decision-making in rapidly urbanizing regions. Research Implications: The HIMA model effectively predicts PM2.5 concentrations, but its complexity increases computational demands, making it challenging for those with limited technical capabilities. The study's focus on Shah Alam and Klang in Malaysia may limit its applicability to other areas and may limit future air quality trend’s accuracy. This research contributes to worldwide initiatives aimed at fulfilling SDGs for goal 3 (Good Health and Well-Being), goal 11 (Sustainable Cities and Communities), and goal 13 (Climate Action). Originality/Value: The study introduces the HIMA model as a novel approach by integrating a Moving Average from Box-Jenkins Methodology adjustment into Holt’s method, demonstrating its improved efficacy for environmental monitoring tasks such as PM2.5 prediction. © 2024, Editora Alumni In. All rights reserved.
|
|---|