00000nam 2200000zi 4500 9.928089 CaOODSP 20251202083852 m o d f cr mn||||||||| 231004t20232023onca ob f000 0 eng d CaOODSP eng rda CaOODSP eng eng fre n-cn--- FB3-6/2023-21E-PDF Brannlund, Johan, author. Predicting changes in Canadian housing markets with machine learning / by Johan Brannlund, Helen Lao, Maureen MacIsaac and Jing Yang. [Ottawa] : Bank of Canada = Banque du Canada, 2023. ©2023 1 online resource (iii, 15 pages) : illustrations (chiefly colour). text txt rdacontent computer c rdamedia online resource cr rdacarrier Staff discussion paper = Document d'analyse du personnel, 1914-0568 ; 2023-21 ISSN assigned to different series. "Last updated: September 29, 2023." Includes bibliographical references (page 15). "This paper examines whether machine learning (ML) algorithms can outperform a linear model in predicting monthly growth in Canada of both house prices and existing home sales. The aim is to apply two widely used ML techniques (support vector regression and multilayer perceptron) in economic forecasting to understand their scopes and limitations. We find that the two ML algorithms can perform better than a linear model in forecasting house prices and resales. However, the improvement in forecast accuracy is not always statistically significant. Therefore, we cannot systematically conclude using traditional time-series data that the ML models outperform the linear model in a significant way. Future research should explore non-traditional data sets to fully take advantage of ML methods"--Abstract, page iii. Includes abstracts in English and French. Housing Prices Canada Forecasting. House buying Canada Forecasting. Support vector machines. Perceptrons. Logement Prix Canada Prévision. Habitations Achat Canada Prévision. Machines à vecteurs supports. Perceptrons. Bank of Canada, issuing body. Staff discussion paper (Bank of Canada) 2023-21. (CaOODSP)9.806273 PDF 557 KB https://publications.gc.ca/collections/collection_2023/banque-bank-canada/FB3-6-2023-21-eng.pdf