Pricing of illiquid debentures using supervised and unsupervised machine learning techniques
Main Article Content
Abstract
Marking illiquid assets to market is challenging due to the scarcity of information that could indicate their fair price. In the case of illiquid debentures, one of the hindrances to figuring out the proper spread for these kinds of assets is the lack of values from prior trading. This paper proposes to assess the spread of illiquid debentures based on their characteristics, information on the issuers' financial health, and market conditions. The presented method uses unsupervised and supervised learning techniques, combining their respective characteristics to solve the illiquid debentures pricing problem, with applications extending to other types of illiquid assets. In experiments, the proposed methodology proved effective for pricing illiquid debentures with no previous spread value.
Article Details
Section
Long Paper
Authors that publish in the Brazilian Review of Finance agree with the following terms:
Authors maintain their moral rights and grant to Review the copyright and the first publication right with their work simultaneously licensed under a Creative Commons Attribution 3.0 License that allows the total or partial copy of the work, including for commercial use, and sharing of the work with recognition of its authors and the initial publication in this journal.
Authors are allowed to take additional contracts separately for non-exclusive distribution of the paper published in this journal (eg, in institutional repositories or to publish as a book chapter), with recognition of its authors and the initial publication in this journal.
Authors are permitted and encouraged to post their work online (eg, in institutional repositories or on their website) at any point before or during the submission process, as this can lead to productive exchanges, as well as increase the impact and citation of the published work.
The contents of the signed articles are the sole responsibility of the authors, remains their responsibility even after the transfer of the copyright. The Review reserves the right to make normative, spelling and grammar changes in the original article in order to maintain the linguistic standards, but will follow the style of the authors. RBFin also reserves the right to translate the article into another language. RBFin may impose a copyright transfer form as a condition for publishing the article.
