
handle: 2183/39444
[Resumen]: En la actualidad, los sistemas de recomendación se han convertido en una herramienta esencial en empresas que se dedican al comercio electrónico o a las redes sociales. Estos sistemas ayudan a personalizar la experiencia del usuario mediante recomendaciones sobre contenido, productos o servicios basándose en su comportamiento previo además de en sus preferencias. Hay diferentes técnicas que utilizan estos sistemas de recomendación, pero este trabajo se centrará en aquellos que utilizan el filtrado colaborativo. Esta técnica consiste en realizar recomendaciones en función de las calificaciones sobre los productos por parte de los usuarios. Se compararán diferentes algoritmos que utilizan este tipo de filtrado para hacer recomendaciones sobre una base de datos de deporte y actividades al aire libre obtenida de Amazon en donde deberán enfrentarse a diferentes desafíos como la escasez de datos o la falta de escalabilidad de los sistemas.
[Abstract]: Nowadays, recommendation systems have turned into an essential tool in the e-commerces and Social Network business. These systems works towards making a personalized experience for each user by making recommendations about content, products or services that fits the costumer profile taking into account his previous behavior and preferences. The recommendation systems have different techniques, but in this document the focus will be those that use collaborative filtering, which consists of making recommendations based on the users previous ratings of products. Different algorithms that use this technique will be contrasted and compared with the objective of making recommendations on a database of products in the area of sports and outdoor activities, obtained from Amazon, where they will need to face different challenges, such as the scarcity of data or the lack of scalability of the systems.
Traballo fin de grao (UDC.FIC). Ciencia e enxeñaría de datos. Curso 2023/2024
Personalized recommendation, Big data, Machine learning, Collaborative filtering, Grandes conjuntos de datos, Matriz dispersa, Sistema de recomendación, Recomendación personalizada, Recommender system, Aprendizaje automático, Filtrado colaborativo, Sparse matrix
Personalized recommendation, Big data, Machine learning, Collaborative filtering, Grandes conjuntos de datos, Matriz dispersa, Sistema de recomendación, Recomendación personalizada, Recommender system, Aprendizaje automático, Filtrado colaborativo, Sparse matrix
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
