Document type
Bachelor thesisPublication date
Publication license
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/124304
Machine learning mediante Microsoft Azure: una aplicación sobre real-state
Journal Title
Authors
Director/Tutor
Additional contribution
Journal ISSN
Volume Title
Abstract
(spa) Este trabajo explica de forma resumida el funcionamiento de la plataforma “Microsoft Azure”. Como veremos, se trata de una plataforma muy potente con diversas aplicaciones donde la característica principal es que todos sus servicios se encuentran en la nube, por lo que no es necesario ningún tipo de infraestructura previa para llevar a cabo proyectos. En concreto, el trabajo se centra en crear varios modelos de machine learning con la finalidad de explicar el funcionamiento del software.
Analizaremos, mediante el caso empírico basado en una inmobiliaria de estados unidos, como sería implementar mediante la aplicación del servicio “Azure Machine Learning” un problema real para predecir y clasificar el valor de las casas en función de sus características. Y veremos si los resultados obtenidos son factibles contrastándolos con otros métodos de clasificación y predicción.
(eng) The following report is about "Microsoft Azure" platform. As we will see, it is a very powerful software with much applications for the business. The main feature is that has all services in the cloud. That is a big advantage because it is not necessary any previous infrastructure to carry out projects. We will focuses on creating several models of machine learning in order to explain the operation with the software. We will analyze, through one empirical case based on a real-state agency located in city of Ames, United States of America. We will implement through Azure Machine Learning module, a real problem about predict and classify the value of houses according to their characteristics. And we will see if the results obtained are feasible by contrasting them with other methods of classification and prediction.
(eng) The following report is about "Microsoft Azure" platform. As we will see, it is a very powerful software with much applications for the business. The main feature is that has all services in the cloud. That is a big advantage because it is not necessary any previous infrastructure to carry out projects. We will focuses on creating several models of machine learning in order to explain the operation with the software. We will analyze, through one empirical case based on a real-state agency located in city of Ames, United States of America. We will implement through Azure Machine Learning module, a real problem about predict and classify the value of houses according to their characteristics. And we will see if the results obtained are feasible by contrasting them with other methods of classification and prediction.
Description
Treballs Finals de Grau en Estadística UB-UPC, Facultat d'Economia i Empresa (UB) i Facultat de Matemàtiques i Estadística (UPC), Curs: 2017-2018, Tutor: Salvador Torra
Related resource
Subject (English)
Citation
Citation
MONTOYA GUIRADO, Daniel. Machine learning mediante Microsoft Azure: una aplicación sobre real-state. [consulted: 8 of October of 2026]. Available at: https://hdl.handle.net/2445/124304