Boosting the Accuracy of Commercial Real Estate Appraisals: An Interpretable Machine Learning Approach

Juergen Deppner; Benedict von Ahlefeldt-Dehn; Eli Beracha; Wolfgang Schaefers

The Journal of Real Estate Finance and Economics · 2023-03-22 · Issue: 2025-08
Research article · Published version of record · CC BY 4.0 · 11,727 words

Original source: Volume 71 · Issue 2 · 314–351

Read article Ask paper agent Open solutions companion →Original PDF

Ask this paper

Full manuscript text
Source-linked passage retrieval

Paper Agent

Agent platform credit

Dr. Freedom Cheteni · Editor in Chief

Research University Journal · JournalOS conception and editorial stewardship

https://orcid.org/0009-0006-3507-0094

This ORCID identifies the human contributor to the agent platform. Source-paper authors retain their own authorship and identifiers.

Manuscript & source record

Title: Boosting the Accuracy of Commercial Real Estate Appraisals: An Interpretable Machine Learning Approach
Human authorship: Juergen Deppner; Benedict von Ahlefeldt-Dehn; Eli Beracha; Wolfgang Schaefers
Source: Complete manuscript edition 2026-10-22
Editorial record: Attributed Creative Commons source edition. Original publication and authorship remain with the source. Hosting is not a new peer-review decision.

Searches this article’s preserved text and returns exact passages. The source paper and its solutions companion have separate records and agents.

Attribution, rights & verification

Original authors / creators: Juergen Deppner; Benedict von Ahlefeldt-Dehn; Eli Beracha; Wolfgang Schaefers
Original publication: The Journal of Real Estate Finance and Economics · Springer US · 2023-03-22 · Issue date 2025-08
Source & version: Authoritative source ↗ · Published version of record
doi:10.1007/s11146-023-09944-1
License & retained notices: CC BY 4.0
© 2023 The Author(s)
Article-specific license evidence ↗
Exact license notice
Rights and permissions Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . Reprints and permissions
Edition changes: Licensed narrative text edition. Original headings, paragraphs and references are preserved with normalized whitespace and layout. Figures, tables, display equations and separately licensed third-party material are not reproduced; use the linked original full text for those elements and definitive pagination. This is an attributed republication, not newly conducted research.
Evidence limits: U.S. NCREIF transactions from 1997–2021; representative data requirements, model opacity and human-origin bias remain; feature importance is not causality; findings do not validate a family-office model or replace professional appraisers.
Retraction / correction check: No retraction or correction notice found in inspected publisher article front matter or Crossref update-to/relation metadata. Publisher HTML and article-specific Crossref record retrieved 2026-10-22; retained raw evidence. No update-to or retraction relation was returned for this DOI. Bounded status check, not exhaustive surveillance of every correction/retraction database. Future notices can change status. Checked 2026-10-22.
Preserved record: Rights and full text checked 2026-10-22. Included in this volume on 2026-10-22. Original source dates remain unchanged.
Download the preserved source
SHA-256 (retrieved artifact): 34e86f396f668296f5a89f2df75623feb4a646070d48cd4e59b8aa060181e0e8
SHA-256 (preserved text edition): a10d010649b9356b99b7e4de743cf232ce219391f11c64bdecf496dfa0bff42f