Forecasting Trends in the Real Estate Market: Analysis of Relevant Determinants

The real estate market in Ukraine, particularly in Kyiv, has experienced significant fluctuations due to the ongoing conflict and associated economic challenges. This research focuses on forecasting trends within the market, with a specific emphasis on price dynamics and the factors influencing these shifts. The actuality of this study stems from the pressing need to understand how the war, macroeconomic instability, and demographic changes impact real estate demand, investment patterns, and property prices. Given the rapid shifts in market dynamics and the complex interplay between economic variables, accurate forecasting is crucial for stakeholders such as investors, policymakers, and analysts. The methodology of this study combines traditional and advanced analytical tools to provide comprehensive and accurate forecasts. A dual-approach forecasting model was employed, using both the Brown-Mayer method implemented in Excel and advanced functionality provided by Statgraphics software. The Brown-Mayer method, which relies on exponential smoothing, allowed for the analysis of basic trends and seasonality in the time series data. Statgraphics, with its capacity to consider complex changes in market dynamics, provided more precise forecasts. The study involved data preparation, anomaly detection, correction, and checks for stationarity to ensure that the forecasts were not distorted by irregularities or missing data. Data were derived from key indicators like the Ukrainian Index of Retail Deposit Rates (UIRD3M), price changes in construction, the National Bank of Ukraine's key interest rate, and the average prices of primary real estate in Kyiv from 2018 to 2023. The findings indicate that Statgraphics was more accurate in forecasting real estate trends in Kyiv than the Brown-Mayer method. The confidence intervals generated by Statgraphics aligned closely with observed price trends, while the Brown-Mayer method showed a larger deviation due to its simpler approach to trend smoothing. The study revealed that external factors such as war-induced economic instability, high interest rates, inflation, and currency devaluation slowed the growth rates of real estate prices, particularly in urban centers like Kyiv. Moreover, the demand for real estate shifted towards rental properties and commercial spaces, particularly warehousing, reflecting changes in business operations and population migration to safer regions. The discussion emphasizes the importance of employing multiple methodologies to enhance forecast reliability. The research underlines that while simpler methods like the Brown-Mayer model are useful for general trends, advanced software tools like Statgraphics are more effective for accurate market prediction in volatile environments. Additionally, the study recommends a holistic approach to future forecasting models by incorporating a wider range of variables and indicators. This would improve model robustness and predictive power, particularly in the context of geopolitical and macroeconomic disruptions. This study contributes to the understanding of real estate market forecasting, providing valuable insights for stakeholders aiming to navigate the complexities of a rapidly changing market landscape in Ukraine. The research highlights the need for adaptive forecasting methods that can account for market volatility and external shocks.