Predictive Modeling based on Machine Learning for retail SMEs, case study Bluefields

Abstract

Nowadays, small and medium-sized enterprises (SMEs) are forced to make use of technology to gain a foothold in the market, taking advantage of the different tools that are emerging and that, consequently, allow them to remain competitive. Therefore, a predictive model based on Machine Learning is an essential tool, its use generates information that allows making decisions that will positively affect business processes. In this sense, the main objective of the project is to develop a predictive model based on Machine Learning aimed at sales SMEs in Bluefields city, Autonomous Region of the South Caribbean Coast, Nicaragua, which serves as a tool to maximize the profits of these companies. The development methodology adopted in the construction of the predictive model was the "waterfall model", which is the best suited to the context of the project. This methodology suggests a systematic and sequential approach, disciplined and based on analysis, design, testing and maintenance. As a result, a predictive model was obtained with the necessary requirements to remedy the deficiencies of these companies. The model is composed of two modules, the first one is the SGPN's Companion that guarantees the storage, manipulation and security of the data, the second module is the Business Process Management System (BPMS) or prediction model, which allows to carry out the business process studies.