Toward Fish Silage Emulsion from Barbados: A Mixture of Experts Analysis
DOI:
https://doi.org/10.47852/bonviewFSI52025821Keywords:
mixture of experts model, fertilizer prices, fish silage emulsion, BarbadosAbstract
Fish silage emulsion is a sustainable alternative to synthetic fertilizers. Fish silage emulsion offers several benefits, including
fertilizing crops, reducing methane emissions, and helping reduce dependence on nitrogenous fertilizers. To assess the market for fish silage emulsion in Barbados, one needs to consider the fertilizer market. This assessment should consider market demand, price, supply, and the potential for export to neighboring countries. This study uses the mixture of experts (MoE) model to forecast fertilizer prices, measured by the Fertilizer Price Index (FPI). The MoE model is a machine learning framework intended to optimize model parameters efficiently while minimizing the corresponding processing requirements. It accomplishes this by utilizing a set of specialized submodels, known as “experts,” along with a gating system that dynamically identifies the most pertinent experts for each input. Using monthly FPI data from January 2021 to February 2025, forecasts were generated. The model projects the index to rise from 133.47 in February 2025 to 153.1040 in the 5-step ahead forecast and further to 200 in the 10-step ahead forecast.
Received: 2 April 2025 | Revised: 26 June 2025 | Accepted: 17 July 2025
Conflicts of Interest
The author declares that he has no conflicts of interest to this work.
Data Availability Statement
The data that support the findings of this study are openly available in https://github.com/doncharles005/MoE and https://wits.worldbank.org/.
Author Contribution Statement
Don Charles: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Author

This work is licensed under a Creative Commons Attribution 4.0 International License.