Predicting real estate price variations using machine learning and google trends

  • Bradley Christopher Begaud (Student)

Student thesis: Master's Thesis


The goal of this paper is to create a modern model via the use of machine learning (such as supportvector regression, regression tree and neural networks) and google trends to predict real estate pricevariations. The model should achieve significant predictive capabilities in monthly variations andshould be both interpretable and not overly complex. There is major interest in being able to predictreal estate prices and many articles have been published on the subject. Most traditional models useeconomic data which are usually published quarterly or annually and thus are not very efficient forshort term predicting. There is interest from the investor point of view in the subject goes, yet it goesbeyond as it is one of the most important costs for a regular family. These models will use as inputsvarious variables that effect either directly or indirectly prices in real estate. We will focus on the Miami metropolitan area or the Miami-Fort Lauderdale-Pompano Beach area. The US market waschosen because it provides the best access to reliable and consistent data. Our model will also focus onpredicting single family house prices which are very popular in the US. Our study has yielded mixedresults as the accuracy of the predictions is either mediocre or decent depending on the model used. However, the accuracy in predicting the direction of the variation is very good with all modelsobtaining 85% or above and one model superior to 95%.
Date of Award18 Oct 2021
Original languageEnglish
Awarding Institution
  • Universidade Católica Portuguesa
SupervisorPaulo Giordani (Supervisor)


  • Machine learning
  • Google trends
  • Real estate
  • Prices
  • Variations
  • Miami


  • Mestrado em Finanças

Cite this