New paper: Testing machine learning systems in real estate
How do ML-models arrive at their predictions? Do they do what we hope they do—or are corners cut?. New paper out at Real Estate Economics
Posts by Tag
- research 10
- publications 4
- artificial intelligence 3
- working papers 2
- ML 2
- real estate 2
- social science 2
- Domain Names 1
- machinelearning 1
- August Potuczek 1
- AI 1
- working paper 1
- idea generation 1
- LLM 1
- authorship 1
- research ethics 1
- academic writing 1
- conference 1
- cambridge 1
research
New Paper: Urban land valuation with bundled good and land residual assumptions
Paper out: This paper develops a new approach to estimate the value of urban land and indirectly tests land residual assumptions. Bonus: Value surfaces estim...
New Working Paper: “Growth and Predictability of Urban Housing Rents”
This paper studies urban rental prices for half a millennium (1500–2020) and seven cities: Amsterdam, Antwerp, Bruges, Brussels, Ghent, London, and Paris. Ba...
Spatial ML: Estimating Land Values in Phoenix (AZ)?
A neural networks that accounts for spatial correlation and time dynamics?
Are Estimates of Rapid Growth in Urban Land Values an Artifact of the Land Residual Model?
New paper out: A closer look at urban land and structure values – this is important for national accounts and for analysis of real estate risk over time. Wit...
Immobilienanlagen: Angebliches Renditewunder entzaubert / Le « miracle » de l’investissement immobilier démystifié
Summary of our total return paper in German and French.
New Publication: The Total Return To Real Estate
New research accepted for publication at the Review of Financial Studies (RFS) suggests that returns to real estate are solid but not exceptional: No sign of...
Machine Learning, Architectural Styles and Property Values
New research accepted for publication at the Journal of Real Estate Finance and Economics: This paper couples a traditional hedonic model with architectural ...
Aesthetic Preferences for Residential Architecture: Finding Ground Truth with Machine Learning Approaches
This paper first collects binary classifications of house pictures from a large group of participants and then trains personalized ML classifiers for each pa...
Valuable Words: The Price Dynamics of Internet Domain Names
This article estimates the first constant quality price index for Internet domain names. The suggested index provides a benchmark for domain name traders and...
publications
Are Estimates of Rapid Growth in Urban Land Values an Artifact of the Land Residual Model?
New paper out: A closer look at urban land and structure values – this is important for national accounts and for analysis of real estate risk over time. Wit...
Immobilienanlagen: Angebliches Renditewunder entzaubert / Le « miracle » de l’investissement immobilier démystifié
Summary of our total return paper in German and French.
New Publication: The Total Return To Real Estate
New research accepted for publication at the Review of Financial Studies (RFS) suggests that returns to real estate are solid but not exceptional: No sign of...
Machine Learning, Architectural Styles and Property Values
New research accepted for publication at the Journal of Real Estate Finance and Economics: This paper couples a traditional hedonic model with architectural ...
artificial intelligence
I, not We: Claiming authorship
One pitfall of using Claude Code and other AI tools is that they make me lazy. The output is slick, useful, and smoothly integrated. The machines tries to gi...
Good Catch! Quality control when working with AI
Over the last few months, I have been working intensively with Claude Code, ChatGPT, and other AI tools. It has been a wild learning experience, and at times...
Using AI for ideas, writing?
I have been looking at the ProudlyHuman de minimis standard and was somewhat surprised that the otherwise purist pro-human stance allows for using AI “to sea...
working papers
New Working Paper: “Growth and Predictability of Urban Housing Rents”
This paper studies urban rental prices for half a millennium (1500–2020) and seven cities: Amsterdam, Antwerp, Bruges, Brussels, Ghent, London, and Paris. Ba...
Aesthetic Preferences for Residential Architecture: Finding Ground Truth with Machine Learning Approaches
This paper first collects binary classifications of house pictures from a large group of participants and then trains personalized ML classifiers for each pa...
ML
New Paper: Urban land valuation with bundled good and land residual assumptions
Paper out: This paper develops a new approach to estimate the value of urban land and indirectly tests land residual assumptions. Bonus: Value surfaces estim...
Spatial ML: Estimating Land Values in Phoenix (AZ)?
A neural networks that accounts for spatial correlation and time dynamics?
real estate
Call for Papers: Real Estate Finance and Investment Symposium 2026
One of the highlights of my year — for the tenth year running — is the Real Estate Finance and Investment Symposium that the Cambridge Real Estate Research C...
Can AI be a PI? Mapping real estate research and testing AI idea generation
Under active development — findings and figures may change.
Domain Names
Valuable Words: The Price Dynamics of Internet Domain Names
This article estimates the first constant quality price index for Internet domain names. The suggested index provides a benchmark for domain name traders and...
machinelearning
New paper: Testing machine learning systems in real estate
How do ML-models arrive at their predictions? Do they do what we hope they do—or are corners cut?. New paper out at Real Estate Economics
August Potuczek
Franz Xaver Rektorzik
Etchings by Franz Xaver Rektorzik, printed by August Potuczek
AI
Can AI be a PI? Mapping real estate research and testing AI idea generation
Under active development — findings and figures may change.
working paper
Can AI be a PI? Mapping real estate research and testing AI idea generation
Under active development — findings and figures may change.
idea generation
Can AI be a PI? Mapping real estate research and testing AI idea generation
Under active development — findings and figures may change.
LLM
Can AI be a PI? Mapping real estate research and testing AI idea generation
Under active development — findings and figures may change.
research ethics
Using AI for ideas, writing?
I have been looking at the ProudlyHuman de minimis standard and was somewhat surprised that the otherwise purist pro-human stance allows for using AI “to sea...
academic writing
I, not We: Claiming authorship
One pitfall of using Claude Code and other AI tools is that they make me lazy. The output is slick, useful, and smoothly integrated. The machines tries to gi...
conference
Call for Papers: Real Estate Finance and Investment Symposium 2026
One of the highlights of my year — for the tenth year running — is the Real Estate Finance and Investment Symposium that the Cambridge Real Estate Research C...
cambridge
Call for Papers: Real Estate Finance and Investment Symposium 2026
One of the highlights of my year — for the tenth year running — is the Real Estate Finance and Investment Symposium that the Cambridge Real Estate Research C...
social science
Good Catch! Quality control when working with AI
1 minute read
Over the last few months, I have been working intensively with Claude Code, ChatGPT, and other AI tools. It has been a wild learning experience, and at times...
Using AI for ideas, writing?
less than 1 minute read
I have been looking at the ProudlyHuman de minimis standard and was somewhat surprised that the otherwise purist pro-human stance allows for using AI “to sea...