Desarrollo de un asistente conversacional para gestión de compra-venta de ropa en línea usando Rasa Open-Source.

Abstract

Technology has generated a significant impact on people's lives and has favored the development of e-commerce. Since the COVID-19 health crisis, social distancing and the closure of businesses have caused commercial activity to increase through digital channels in Ecuador. Although several businesses chose to hire more staff, it was not enough due to the high volume of questions they received. Chatbots offer immediate attention 24/7 and thus avoid the abandonment of shopping carts. Although efforts have been made to improve the effectiveness of chatbots, through machine learning algorithms, conversations remain rigid and with responses, in some cases, undesirable. This is because the context and history of the conversation between the chatbot and the user have not been considered. For this reason, this work proposes the development of a conversational assistant capable of accompanying the client throughout the clothing discovery process, using Rasa; a framework that combines the comprehension and processing of natural language based on transformer-type neural networks, allowing to improve the effectiveness of the responses of said assistant. In addition, Rasa was combined with a search engine “Algolia” to enhance the assistant's abilities to find the requested clothing and deliver instant results. Finally, the results of this work showed that through Rasa it is possible to create assistants as personalized as desired and that incorporating continuous training and evaluation processes with real users makes it possible for the model to be generalized to real-world scenarios, thus increasing the rate effectiveness.