Predictive Model in Production through Progressive Web Applications to Forecast Moniliasis in Cacao.

Abstract

Cocoa is considered a significant crop in Ecuador, as it represents a favorable source of income for the country's economy, thanks to the remarkable quality of the product. However, it faces a significant issue in its crops: moniliasis, a fungal disease that attacks cocoa cultivation, is present in most Latin American countries. Consequently, this leads to decreased cocoa production and a lower final product quality. The study focuses on designing a predictive production model through a progressive web application to forecast moniliasis in cocoa. The objective is to create an application that anticipates the presence of this disease, thereby contributing to the improvement of the local economy for all farmers. Various methodologies were employed, including bibliographic methods, design science research methodology, and machine learning models. The results obtained from this research indicate that the Gradient Boosting Classifier is the algorithm that best fits the provided dataset. Once this algorithm was identified, a progressive web application was developed and made available for public use by farmers. Furthermore, the efficiency of the predictive model was verified using the statistical method of central tendency, demonstrating that the predictive model is beneficial, primarily by saving farmers a significant amount of time. Anticipating the disease enables timely preventive and corrective measures, which could reduce losses in cocoa production and enhance the quality of the final product. Keywords: cacao, moniliasis, predictive model, progressive web apps, supervised learning.