About the Journal

Aims

The Valuation Engineer Journal advances the theory and practice of real-estate valuation as a rigorous, data-driven, and reproducible discipline. It bridges the long-standing gap between traditional appraisal practice and modern statistical and computational methods, giving appraisers, analysts, and researchers a venue to develop, document, and critique quantitative valuation techniques — and to hold them to engineering standards of transparency, testability, and reproducibility.

Scope

The Journal welcomes contributions on, among other related topics:

  - Statistical and machine-learning methods for valuation — multivariate adaptive regression splines (MARS), regularized regression (lasso, ridge,
  elastic net), generalized additive models, and tree-based and ensemble methods
  - Automated valuation models (AVMs) and hybrid appraiser–model workflows
  - Residual analysis and constraint-based approaches to estimating subjective feature value
  - Data sources, quality, and feature engineering for valuation (MLS and alternative data)
  - Reproducibility, open data, and open-source software/tools (R, Python) for valuation
  - Appraisal theory, methodology, standards (e.g., USPAP), and the doctrine–practice interface
  - Valuation accuracy, uncertainty quantification, and appraisal bias and equity
  - Mass appraisal, assessment, and market-area analysis
  - Legal, regulatory, and ethical developments affecting valuation
  - Applications of these methods to asset classes beyond residential real estate

Audience

Practicing appraisers and valuation professionals, assessors, quantitative analysts and data scientists, researchers, educators, and students.

What we publish

Research and methodology articles, software and tool guides, editorials, letters to the editor, commentary on recent court cases, and open problems and topics in need of authors.

Editorial Model

The Valuation Engineer Journal uses an AI-assisted editorial review model. In place of traditional anonymous peer review, each submission is assessed by the Editor-in-Chief with the assistance of advanced AI systems that evaluate methodology, internal consistency, reproducibility, clarity, and coverage of the relevant literature. We adopt this model deliberately and disclose it openly: for the quantitative, reproducible work this Journal publishes, we believe AI-assisted review provides faster, more consistent, and more transparent scrutiny than conventional peer review. We complement it with open post-publication discourse — readers are encouraged to submit Letters to the Editor and corrections — and the model will continue to evolve.  Each published article carries a Crossref DOI resolving it to this site, with a parallel preservation copy deposited at Zenodo under its own versioned DOI.

Disclaimer

Views expressed are those of the authors and do not constitute appraisal, legal, or investment advice. Methods described herein must be applied by qualified professionals in conformance with applicable professional standards (e.g., USPAP) and the laws of their jurisdiction.  The journal, its editor, and its publisher accept no liability for decisions made in reliance on published content.