Session

Management Business and Economy

Description

This study employs the Random Forest (RF) algorithm to forecast housing prices in Prishtina, analyzing 1,468 transactions from 2019 to 2023, using Python. It segments the data for optimal model training and validation, focusing on critical attributes like property area and proximity to key urban features. Performance is assessed through MSE, R², MAE, and RMSE, highlighting RF's accuracy. A variable importance test further elucidates the significant predictors of price, underscoring the impact of location and infrastructure. The study's implications extend to real estate valuation practices, offering a methodological framework for leveraging machine learning in emerging markets

Keywords:

Random Forest, Real Estate Valuation, Predictive Modelling, Variable Importance, Emerging Markets, Prishtina.

Proceedings Editor

Edmond Hajrizi

ISBN

978-9951-982-15-3

Location

UBT Kampus, Lipjan

Start Date

25-10-2024 9:00 AM

End Date

27-10-2024 6:00 PM

DOI

10.3107/ubt-ic.2024.28

Download

Included in

Business Commons

Share

COinS
 
Oct 25th, 9:00 AM Oct 27th, 6:00 PM

Enhancing Real Estate Valuation in Emerging Markets: A Random Forest Approach in Prishtina

UBT Kampus, Lipjan

This study employs the Random Forest (RF) algorithm to forecast housing prices in Prishtina, analyzing 1,468 transactions from 2019 to 2023, using Python. It segments the data for optimal model training and validation, focusing on critical attributes like property area and proximity to key urban features. Performance is assessed through MSE, R², MAE, and RMSE, highlighting RF's accuracy. A variable importance test further elucidates the significant predictors of price, underscoring the impact of location and infrastructure. The study's implications extend to real estate valuation practices, offering a methodological framework for leveraging machine learning in emerging markets