Análisis predictivo del potencial comercial de industrias en el Ecuador para una empresa gestora ambiental

Abstract

The present research is developed in the context of industrial waste management and the transition toward circular economy models in Ecuador, where environmental management companies face the challenge of identifying and prioritizing industrial clients with high commercial potential. Therefore, the objective of this study is to develop a commercial intelligence system based on predictive analytics that estimates the probability of industrial companies converting into effective clients. This approach is justified by the need to reduce reliance on empirical criteria and to optimize commercial decision-making using structured data. During the development of the project, a quantitative approach was applied, integrating information from internal sources of an environmental management company with public databases obtained from official institutions. Data cleaning, normalization, and integration processes were performed, incorporating firmographic, financial, contextual, and environmental variables. Subsequently, supervised machine learning models were trained and validated to evaluate their predictive performance. The results showed that the developed model made it possible to assign a conversion score to each company, improving prospect prioritization and reducing the operational workload associated with manual prospecting. Additionally, greater alignment between marketing and sales criteria was observed. In conclusion, the proposed system contributes to strengthening operational efficiency, commercial intelligence, and data-driven decision-making in the Ecuadorian industrial sector. Keywords: Industrial waste management, Commercial intelligence, Predictive analytics, Machine learning, Client prospecting.