Desarrollo de un prototipo de sistema web basado en machine learning para la identificación de tendencias y análisis de incidentes de la empresa de seguridad privada PROTEMAXI.

Abstract

This work is the construction and research of a prototype web system based on Machine Learning, intelligent automation is a new way to enhance the automation of traditional processes with artificial intelligence, PROTEMAXI a company that provides security service to its customers within the city of Guayaquil has the need to streamline the process of generating reports of developments reported monthly while analyzing it for valuable information, commonly this process is done manually but is inaccurate and may contain errors; For this reason the present project is based on the construction of the prototype of the system that generates automated reports according to the client and the date that is to say the period integrating the technology of the automatic learning; The construction of the system was made with the technological requirements that the company requested as the Laravel Framework for the web interface and for the Machine Learning Python model. From the different information gathering meetings to the development of the Machine Learning model, a cascade software methodology was used, which allows working in a more direct way and without requesting unestablished changes. The objectives of the project are based on the implementation of the use of Machine Learning techniques to generate results based on the patterns found, the development of the web system, the creation of a database and the use of the technologies required by the company in terms of compatibility. Finally, the project concludes with the generation of reports according to the client and the selected month where preloaded data and the results of the analysis of the Machine Learning model are shown, thanks to this implementation it is possible to reduce the time of generation of the report and frequency patterns are obtained about the new developments that occurred and recommendations that can be taken in this regard.