Desarrollo de aplicación web e-commerce con recomendación de contenido para una tienda online de cosméticos.

Abstract

Over the years, the Internet has been consolidated in people's daily lives, becoming present in a large part of the activities that are carried out on a daily basis, from entertainment to telemedicine in the area of health. It has been more favored with the emergence of the Covid-19 virus, because biosecurity measures such as isolation were implemented in response to this virus, favoring certain sectors such as streaming entertainment and electronic commerce, among others; Focusing on electronic commerce, it can be identified that it has been positioning itself in the market and in recent years it has had a considerable increase due to the fact that several SMEs found it necessary to adapt their commercial activities based on the measures implemented by governments. Electronic commerce offers several benefits and today that it has a great reach in the population it is widely used in companies, in this work an E-commerce web application with content recommendation for an online cosmetics store was developed, with this application It was proposed to create a platform that allows the dissemination and commercialization of the available products, in addition a key aspect is the implementation of a recommendation system, which is generally categorized as based on content, collaborative filtering and hybrids, depending on the system, algorithms are developed that facilitate recommending products that are related to a specific user profile based on the information obtained from the web application, to develop this techniques such as cosine similarity, Pearson's correlation coefficient, matrix factorization, TF-IDF were applied. In addition, software development involves multiple activities that must be controlled and managed properly, for this the Extreme Programming (XP) agile development methodology was used and in the coding stage a three-layer client-server architecture was implemented, in which which technologies were used such as: MongoDB in the data layer for the persistence of information, in the logic layer Node.js was used to create a Rest API to access the information from the database and Flask was used to implement the recommendation system with the Python language, for the recommendations systems based on content and collaborative filter were implemented in order to obtain recommendations as results that do not necessarily need a history of the client, finally in the client layer the Frontend was developed with the Angular framework which offers a semi-structured framework for developing web applications.