Paper: arXiv 2505.09620
Authors: Nicolas Houlié
Abstract
I show that house prices can be modeled using machine learning (kNN and tree-bagging) and a small dataset composed of macro-economic factors (MEF), including an inflation metric (CPI), US treasury rates (10-yr), Gross Domestic Product (GDP), and portfolio size of central banks (ECB, FED). This set of parameters covers all the parties involved in a transaction (buyer, seller, and financing facility) while ignoring the intrinsic properties of each asset and encompassing local (inflation) and liquidity issues that may impede each transaction composing a market. The model here takes the point of view of a real estate trader who is interested in both the financing and the price of the transaction. Machine Learning allows for the discrimination of two periods within the dataset. Unconventional policies of central banks may have allowed some institutional investors to arbitrage between real estate returns and other bond markets (sovereign and corporate). Finally, to assess the models’ relative performances, I performed various sensitivity tests, which tend to constrain the possibilities of each approach for each need. I also show that some models can predict the evolution of prices over the next 4 quarters with uncertainties that outperform existing index uncertainties.
Complexity vs Empirical Score
- Math Complexity: 2.5/10
- Empirical Rigor: 6.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper uses accessible machine learning models (kNN, tree-bagging) with no advanced mathematical derivations, but implements sensitivity tests and compares predictions to existing indices using macroeconomic data from multiple countries over decades, making it practical and data-heavy.
Research Flowchart
flowchart TD
A["Research Goal: Model Real Estate Prices via Macro-Economic Factors"] --> B["Data Collection & Feature Selection"]
B --> C["Machine Learning Modeling"]
C --> D["Sensitivity & Uncertainty Analysis"]
D --> E["Key Findings & Outcomes"]
subgraph B ["Inputs"]
B1["MEFs: GDP, CPI, 10-yr Treasury"]
B2["Central Bank Assets: ECB, FED"]
end
subgraph C ["Models"]
C1["kNN"]
C2["Tree-Bagging"]
C3["Period Discrimination"]
end
subgraph E ["Outcomes"]
E1["Predict 4-Quarter Price Trends"]
E2["Identify Arbitrage in Unconventional Policy Era"]
E3["Outperform Index Uncertainties"]
end
B1 & B2 --> C
C1 & C2 & C3 --> D
D --> E1 & E2 & E3
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes modeling house prices with machine learning (kNN and tree‑bagging) using a small macro‑economic dataset.
Source sentence
I show that house prices can be modeled using machine learning (kNN and tree-bagging) and a small dataset composed of macro-economic factors (MEF), including an inflation metric (CPI), US treasury rates (10-yr), Gross Domestic Product (GDP), and portfolio size of central banks (ECB, FED).
Assumes
No explicit assumptions found in the text.
Data
- Swiss National Bank dataset macro unknown
Source sentence
I have used three different sources for the data used in this study. First, I used the Swiss National Bank (SNB) dataset, which helped me to identify which parameters were critical to include.
- FRED database macro public
Source sentence
Second, and from the parameter selection, I have built an initial model based on inflation, financing rates, and GDP to explain the price evolution in 15 countries using the data already archived by the FRED database.
- ECB/FED portfolio size macro unknown
Source sentence
portfolio size of central banks (ECB, FED).
Costs
Not applicable
Finds 5
- The “lightdata” model using fewer inputs but a longer period achieves good performance (RMS < 15, MAPE < 0.2, COR > 0.90). performance
Source sentence
I consider both models are performing well (RMS< 15; MAPE< 0.2; COR>0.90).
- Adding central‑bank rate data has minimal impact for France but a slight improvement for Switzerland after 2015. performance
Source sentence
In Switzerland, we can find a slight improvement over the most recent years (> 2015).
- The level of 10‑year interest rates is identified as the most critical parameter for house‑price dynamics. statistical
Source sentence
the most critical parameter is the level of interest rates at 10 years
- Some models can predict house‑price evolution for the next four quarters with uncertainties better than existing indexes. predictive-accuracy
Source sentence
some models are performing well enough to predict prices over the next 4 quarters.
- Correlation between Swiss house‑price changes and ECB portfolio size exceeds 92% over the last 24 quarters. statistical
Source sentence
The correlation coefficient between prices in Switzerland and ECB portfolio size is higher than 92% (computed over the last 24 quarters...
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 25 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (60)
- Stock Market Response to Quantitative Easing: Evidence from the Novel Rolling Windows Nonparametric Causality-in-Quantiles Approach (2023) — link
- Does hedonism influence real estate investment decisions? The moderating role of financial self-efficacy (2023) — link
- Monetary policy spillover to small open economies: Is the transmission different under low interest rates? (2023) — link
- House Prices and Marriage in Spain (2022) — link
- The impact of crimes on house prices in LA County (2022) — link
- Learning low‐dimensional structure in house price indices (2021) — link
- Dynamic implications of GDP, interest rates, taxes, income, foreign direct investments, housing prices on property NPLs (2021) — link
- The determinants of real estate prices in a European context: a four-level analysis (2021) — link
and 52 more
- Leading indicators for US house prices: New Evidence and Implications for EU Financial Risk Managers (2021) — link
- HOUSE PRICES, RENTAL COSTS, AND MORTGAGE INTEREST RATES (2021) — link
- THE SPECIAL EFFECT OF INTEREST RATE CUTS ON HOUSING PRICES (2021) — link
- Which stocks are driven by which interest rates? (2021) — link
- Artificial Intelligence for Modeling Real Estate Price Using Call Detail Records and Hybrid Machine Learning Approach (2020) — link
- The Importance of Economic Variables on London Real Estate Market: A Random Forest Approach (2020) — link
- Using Machine Learning Models and Actual Transaction Data for Predicting Real Estate Prices (2020) — link
- COVID-19 Infects Real Estate Markets: Short and Mid-Run Effects on Housing Prices in Campania Region (Italy) (2020) — link
- A New World Post COVID-19 (2020) — link
- Does Immigration Affect Residential Real Estate Prices? Evidence From Australia (2020) — link
- Big data analytics predicting real estate prices (2020) — link
- The U.S. Housing Bubble: Implications for Monetary Policy and the Global Supply of Saving (2019) — link
- Sensitivity Analysis of Machine Learning Models for the Mass Appraisal of Real Estate. Case Study of Residential Units in Nicosia, Cyprus (2019) — link
- Real estate prices and systemic banking crises (2019) — link
- Are housing prices improving GDP or vice versa? A cross-regional study of China (2018) — link
- Stock market reaction to policy interventions (2018) — link
- Transmission of shocks across global real estate and equity markets: An examination of the 2007–2008 housing crisis (2018) — link
- Financial Globalization and Bank Lending: The Limits of Domestic Monetary Policy? (2018) — link
- The impact of micro urban space structure on land price of commercial real estate (2017) — link
- Housing Markets and Unconventional Monetary Policy (2016) — link
- Inflation protected investment strategies (2016) — link
- Misinformed Speculators and Mispricing in the Housing Market (2016) — link
- Speculative Bubble Spillovers across Regional Housing Markets (2015) — link
- Real estate price forecasting based on SVM optimized by PSO (2014) — link
- House price dynamics and their reaction to macroeconomic changes (2013) — link
- Land Leverage and House Prices (2011) — link
- An R Companion to Applied Regression (2010)
- MONETARY POLICY, CREDIT EXTENSION, AND HOUSING BUBBLES: 2008 AND 1929 (2009) — link
- Building Predictive Models in R Using the caret Package (2008) — link
- Illiquidity and Pricing Biases in the Real Estate Market (2007) — link
- REAL ESTATE PRICE PREDICTION MODEL BASED ON FUZZY NEURAL NETWORKS (2005) — link
- Semiparametric Construction of Spatial Generalized Hedonic Models for Private Properties (2005)
- Real Estate Prices and Economic Cycles (2002)
- Real Estate and the Macroeconomy (2000) — link
- Hedging Portfolios with Real Assets (1995) — link
- The Real Estate Cycle and the Economy: Consequences of the Massachusetts Boom of 1984-87 (1992) — link
- Gambling on Real Estate: Limited Rationality in the Global Economy (1991) — link
- Inversion of seismic reflection data in the acoustic approximation (1984) — link
- Factors Affecting Real Estate Prices During the COVID-19 Pandemic: An Empirical Study in Vietnam (2021)
- Chapter 11 – Housing Bubbles (2015) — link
- Essays on monetary policy and asset price bubbles: evidence from the U.S. housing bubble (2015)
- Crash and Beyond (2013)
- The Relationship of House Price Rising Rate and GDP Growth Rate (2011) — link
- A cross-country quarterly database of real house prices: a methodological note (2011) — link
- Alternative Investments for Institutional Investors: Risk Budgeting Techniques in Asset Management and Asset-Liability Management (2009)
- Impact of Harbin no one subway to real estate price (2007)
- House price, interest rate and macroeconomic fluctuation: Evidence from Shanghai real estate market (2007)
- The U.K. Housing Market: Bubbles and Buyers (2004)
- Industrial and Business Forecasting Methods (1982)
- Market-Stabilization QE
- The Effect of Heuristics and Biases on Real Estate Valuation and Cyclicality
- Unintended Consequences of QE: Real Estate Prices and Financial Stability
0 of 60 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.