House Price Prediction

  • Nawar Aghi
  • Ahmad Abdulal

Student thesis: Bachelor

Abstract

This study proposes a performance comparison between machine learning regression algorithms and Artificial Neural Network (ANN). The regression algorithms used in this study are Multiple linear, Least Absolute Selection Operator (Lasso), Ridge, Random Forest. Moreover, this study attempts to analyse the correlation between variables to determine the most important factors that affect house prices in Malmö, Sweden. There are two datasets used in this study which called public and local. They contain house prices from Ames, Iowa, United States and Malmö, Sweden, respectively.The accuracy of the prediction is evaluated by checking the root square and root mean square error scores of the training model. The test is performed after applying the required pre-processing methods and splitting the data into two parts. However, one part will be used in the training and the other in the test phase. We have also presented a binning strategy that improved the accuracy of the models.This thesis attempts to show that Lasso gives the best score among other algorithms when using the public dataset in training. The correlation graphs show the variables' level of dependency. In addition, the empirical results show that crime, deposit, lending, and repo rates influence the house prices negatively. Where inflation, year, and unemployment rate impact the house prices positively.

Date of Award2020-Aug-13
Original languageEnglish
SupervisorQinghua Wang (Supervisor) & Niklas Gador (Examiner)

Educational program

  • Bachelor programme in Computer Software Development

University credits

  • 15 HE credits

Swedish Standard Keywords

  • Computer Sciences (10201)

Keywords

  • multiple linear regression
  • lasso regression
  • ridge regression
  • random forest regression
  • artificial neural network
  • machine learning
  • house price prediction

Cite this

'