Please use this identifier to cite or link to this item:
http://hdl.handle.net/10071/28947
Author(s): | Trigueiros, D. Sam, C. |
Date: | 2018 |
Title: | Discovering the optimal set of ratios to use in accounting-based models |
Journal title: | International Journal of Society Systems Science |
Volume: | 10 |
Number: | 2 |
Pages: | 110 - 131 |
Reference: | Trigueiros, D., & Sam, C. (2018). Discovering the optimal set of ratios to use in accounting-based models. International Journal of Society Systems Science, 10(2), 110-131. https://dx.doi.org/10.1504/IJSSS.2018.10013669 |
ISSN: | 1756-2511 |
DOI (Digital Object Identifier): | 10.1504/IJSSS.2018.10013669 |
Keywords: | Knowledge extraction Financial analysis Financial ratios Financial technology Fintech Accounting models Bankruptcy prediction Financial misstatement detection Earnings forecasting |
Abstract: | Ratios are the prime tool of financial analysis. In predictive modelling tasks, however, the use of ratios raises difficulties, the most obvious being that, in a multivariate setting, there is no guarantee that the collection of ratios eventually selected as predictors will be optimal in any sense. Using, as starting-point, a formal characterisation of cross-sectional accounting numbers, the paper shows how the multilayer perceptron can be trained to create internal representations which are an optimal set of ratios for a given modelling task. Experiments suggest that, when such ratios are utilised as predictors in well-known modelling tasks, performance improves on that reported by the extant literature. |
Peerreviewed: | yes |
Access type: | Open Access |
Appears in Collections: | ISTAR-RI - Artigos em revistas científicas internacionais com arbitragem científica |
Files in This Item:
File | Size | Format | |
---|---|---|---|
article_48675.pdf | 345,81 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.