Comparative Analysis of Forecasting Techniques for Enhancing Coconut Oil Export Predictions in the Philippines

Abstract

In the agricultural domain, the accurate forecasting of crop yields is crucial for economic stability and planning. The Philippines, being one of the world’s largest producers of coconut oil, has a significant portion of its agricultural sector influenced by the predictability of this commodity’s yield. While traditional forecasting methods have been employed, their accuracy fluctuates, necessitating the exploration of more reliable techniques. This study evaluates Grey Forecasting, Moving Average, Forecast by Forecasting Sheet, and Regression Analysis methods for predicting coconut oil production, comparing them over two decades. Through rigorous statistical analysis using measures like MAD, MSE, and MAPE. Grey Forecasting emerges as more consistent and accurate. In 2023, there was an increase of approximately 13.86% compared to 2022. In 2024, this figure rose to about 25.08% compared to 2023. Similarly, in 2025, there was an increase of roughly 18.17% compared to 2024. The study's contribution lies in its comprehensive long-term data analysis, offering new insights into Grey Forecasting's application. These findings could significantly impact Philippine agricultural planning and policies, prompting further research to refine forecasting methods. Emphasizing the value of advanced predictive models in agriculture, the study advocates for informed decision-making and resource allocation. Future research should focus on refining these models by incorporating broader datasets and advanced algorithms to improve accuracy and reliability.