“Location, Location, Location”: Fluctuations in Real Estate Market Values after COVID-19 and the War in Ukraine Based on Econometric and Spatial Analysis, Random Forest, and Multivariate Regression

Abstract

In this research, the authors aim to detect the marginal appreciation of construction and neighbourhood characteristics of property prices at three different time points: before the COVID-19 pandemic, two years after the first COVID-19 alert but before the War in Ukraine, and one year after the outbreak of the War. The marginal appreciations of the building’s features are analysed for a pilot case study in Northern Italy using a Random Forest feature importance analysis and a Multivariate Regression. Several techniques are integrated into this study, such as computer programming in Python language, multi-parametric value assessment techniques, feature selection procedures, and spatial analysis. The results may represent an interesting ongoing monitoring of how these anomalous events affect the buyer’s willingness to pay for specific characteristics of the buildings, with particular attention to the location features of the neighbourhood and accessibility.

What are tenants demanding the most? A machine learning approach for the prediction of time on market

“…Furthermore, a comparison between the city of Munich and its outskirts might be an interesting indication of differences between urban and rural residential demand. Following Gabrielli et al (2023) a comparison at different time points could provide further insights into the reaction of time on market to changes in its dwelling specific and neighborhood specific factors. Furthermore, a fair model comparison to the commonly applied Cox proportional hazard model could be insightful.…”

“…For the Ames dataset they find lasso regression and random forest to perform best by means of MAPE. A recently published article by Gabrielli et al (2023) The prediction of time on market analyzes the marginal effect of dwelling specific factors and neighborhood factors on the property price in Padova, Northern Italy, at three different time points: first, 2019 before the COVID-19 pandemic, second, 2021 two years after the first COVID-19 onset however before the war in Ukraine and third, 2023 one year after the war in Ukraine started. They apply a random forest feature importance analysis to exclude the variables with low significance levels from the regression analysis.…”

“…In this paper we summarize the first two dimensions to urban amenities. Following Gabrielli et al (2023) urban amenities can be further classified into supply services or open-air amities. Supply services include healthcare facilities (e.g.…”

Comparative analysis of different approaches to the Ukrainian residential property market evolution modelling and its forecast for the years 2019–2024

“…Studies often rely on historical data and statistical techniques like regression analysis and time-series modelling, focusing on economic factors and their impact on prices. For example, Gabrielli et al (2023) investigated the impact of extraordinary events on preferences in Italy, but their findings might not translate directly to the unique situation in Ukraine. Similarly, Rehman et al (2020) explored the relationship between oil prices and property prices across diverse countries, but their focus on economic factors overlooks the potential influence of political instability or social unrest.…”

Residual energy use and energy efficiency improvement of European supermarket facilities during the post-COVID and energy crisis period

“…In the first half of October 2021, the average electricity price reached a new record of 202.77 euros (€) per megawatt hour (MWh), which is 30 % higher than the previous month's price of 156 €/MWh in September 2021 [ 7 ]. The current energy crisis has resulted in higher product costs at supermarkets and decreased profits for commercial companies [ [8] , [9] , [10] ]. According to the World Bank, energy prices are expected to continue rising throughout 2023, with no short-term relief in sight [ 11 ].…”