54,000 PRIIPs KIDs - how to read them (all)

Adrien Amzallag

Chapter 12 in Artificial Intelligence and Financial Behaviour, 2023, pp 215-239 from Edward Elgar Publishing

Abstract: This chapter presents the results of an ESMA pilot exercise to apply natural language processing techniques on a unique dataset of c. 54 000 Key Information Documents that describe structured retail products produced under the Packaged Retail Investment and Insurance-Based Products Regulation. The techniques involved include measuring linguistic richness and semantic uncertainty, as well as sentiment analysis. This work - an application of SupTech - aims to illustrate how these techniques can produce useful measures for European supervisors, policymakers and risk analysts. Information extracted from text opens up new possibilities for supervisory assessments, for example with respect to information completeness and to legal requirements that a document be comprehensible to investors. In addition, text-based information is uncorrelated with (i.e. complementary to) numerical information, which can help policymakers determine if the legislation is working as intended. Lastly, text-based information can identify new sources of financial risks to investors.

Keywords: Economics and Finance; Innovations and Technology (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.elgaronline.com/view/edcoll/9781803923154/9781803923154.00020.xml (application/pdf)
Our link check indicates that this URL is bad, the error code is: 503 Service Temporarily Unavailable

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:elg:eechap:21559_12

Ordering information: This item can be ordered from
http://www.e-elgar.com

Access Statistics for this chapter

More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Darrel McCalla ().