Abstract
Real estate has always been an important asset class. Massive investment in real estate since the financial crisis 2008 has pushed the demand for integrated and micro-based risk modeling. The data for such risk management is available to banks and other investors, but is not structured and therefore not model-ready. Appraisals are available as printouts as well as pdf files, but the relevant data is only available in semi-structured form and differs by appraisal. A central issue in integrated real estate risk management consists of transferring the relevant information from appraisals into a risk management environment without too much unnecessary human effort. The goal of this article is to describe an approach to identifying and extracting existing semi-structured appraisal information into structured information ready to be consumed by risk models and other applications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
DSCR—debt service coverage ratio is the quotient of net operation income and debt service.
- 2.
NLTK—natural language toolkit is a platform for building Python programs to handle human language data see NLTK Project (2018).
- 3.
Uncleaned, unprocessed character string.
- 4.
Only the table identification is not included in the simple packages.
- 5.
Some see tokenization as a part of the natural language processing.
- 6.
Stemming is the process of transforming words into unified (non-conjugated or declined) words relevant to content.
- 7.
For details on Table 2Vec, see Deng (2018).
Literature
Deng, L. (2018). Table2Vec: Neural word and entity embeddings for table population and retrieval. Stavanger: University of Stavanger.
Enzinger, P., & Grossmann, S. (2019). Managing internal and external network complexity. In V. Liermann & C. Stegmann (Eds.), The impact of digital transformation and fintech on the finance professional. New York: Palgrave Macmillan.
Liermann, V., Li, S., & Schaudinnus, N. (2019). Deep learning—An introduction. In V. Liermann & C. Stegmann (Eds.), The impact of digital transformation and fintech on the finance professional. New York: Palgrave Macmillan.
Liermann, V., Viets, N., & Grossmann, S. (2018, August). Retrieved September 19, 2018, from www.risknet.de https://www.risknet.de/themen/risknews/a-holistic-approach-to-real-estate-risk-management/5a179b5d33c31dd70fa3743aa91f23a6/.
Markowitz, H. M. (1952). Portfolio selection. Journal of Finance, 7, 77–91.
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Mountain View: Google Inc.
NLTK Project. (2018, November 17). Natural language toolkit—Home. Retrieved from Natural Language Toolkit https://www.nltk.org/.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 The Author(s)
About this chapter
Cite this chapter
Liermann, V., Schaudinnus, N. (2019). Real Estate Risk: Appraisal Capture. In: Liermann, V., Stegmann, C. (eds) The Impact of Digital Transformation and FinTech on the Finance Professional. Palgrave Macmillan, Cham. https://doi.org/10.1007/978-3-030-23719-6_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-23719-6_11
Published:
Publisher Name: Palgrave Macmillan, Cham
Print ISBN: 978-3-030-23718-9
Online ISBN: 978-3-030-23719-6
eBook Packages: Economics and FinanceEconomics and Finance (R0)