@inproceedings{arno-etal-2023-numbers,
title = "From Numbers to Words: Multi-Modal Bankruptcy Prediction Using the {ECL} Dataset",
author = "Arno, Henri and
Mulier, Klaas and
Baeck, Joke and
Demeester, Thomas",
editor = "Chen, Chung-Chi and
Huang, Hen-Hsen and
Takamura, Hiroya and
Chen, Hsin-Hsi and
Sakaji, Hiroki and
Izumi, Kiyoshi",
booktitle = "Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing",
month = nov,
year = "2023",
address = "Bali, Indonesia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.finnlp-2.2",
doi = "10.18653/v1/2023.finnlp-2.2",
pages = "11--21",
abstract = "In this paper, we present ECL, a novel multimodal dataset containing the textual and numerical data from corporate 10K filings and associated binary bankruptcy labels. Furthermore, we develop and critically evaluate several classical and neural bankruptcy prediction models using this dataset. Our findings suggest that the information contained in each data modality is complementary for bankruptcy prediction. We also see that the binary bankruptcy prediction target does not enable our models to distinguish next year bankruptcy from an unhealthy financial situation resulting in bankruptcy in later years. Finally, we explore the use of LLMs in the context of our task. We show how GPT-based models can be used to extract meaningful summaries from the textual data but zero-shot bankruptcy prediction results are poor. All resources required to access and update the dataset or replicate our experiments are available on github.com/henriarnoUG/ECL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arno-etal-2023-numbers">
<titleInfo>
<title>From Numbers to Words: Multi-Modal Bankruptcy Prediction Using the ECL Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Henri</namePart>
<namePart type="family">Arno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Klaas</namePart>
<namePart type="family">Mulier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joke</namePart>
<namePart type="family">Baeck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Demeester</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hen-Hsen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Sakaji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiyoshi</namePart>
<namePart type="family">Izumi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bali, Indonesia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present ECL, a novel multimodal dataset containing the textual and numerical data from corporate 10K filings and associated binary bankruptcy labels. Furthermore, we develop and critically evaluate several classical and neural bankruptcy prediction models using this dataset. Our findings suggest that the information contained in each data modality is complementary for bankruptcy prediction. We also see that the binary bankruptcy prediction target does not enable our models to distinguish next year bankruptcy from an unhealthy financial situation resulting in bankruptcy in later years. Finally, we explore the use of LLMs in the context of our task. We show how GPT-based models can be used to extract meaningful summaries from the textual data but zero-shot bankruptcy prediction results are poor. All resources required to access and update the dataset or replicate our experiments are available on github.com/henriarnoUG/ECL.</abstract>
<identifier type="citekey">arno-etal-2023-numbers</identifier>
<identifier type="doi">10.18653/v1/2023.finnlp-2.2</identifier>
<location>
<url>https://aclanthology.org/2023.finnlp-2.2</url>
</location>
<part>
<date>2023-11</date>
<extent unit="page">
<start>11</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Numbers to Words: Multi-Modal Bankruptcy Prediction Using the ECL Dataset
%A Arno, Henri
%A Mulier, Klaas
%A Baeck, Joke
%A Demeester, Thomas
%Y Chen, Chung-Chi
%Y Huang, Hen-Hsen
%Y Takamura, Hiroya
%Y Chen, Hsin-Hsi
%Y Sakaji, Hiroki
%Y Izumi, Kiyoshi
%S Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing
%D 2023
%8 November
%I Association for Computational Linguistics
%C Bali, Indonesia
%F arno-etal-2023-numbers
%X In this paper, we present ECL, a novel multimodal dataset containing the textual and numerical data from corporate 10K filings and associated binary bankruptcy labels. Furthermore, we develop and critically evaluate several classical and neural bankruptcy prediction models using this dataset. Our findings suggest that the information contained in each data modality is complementary for bankruptcy prediction. We also see that the binary bankruptcy prediction target does not enable our models to distinguish next year bankruptcy from an unhealthy financial situation resulting in bankruptcy in later years. Finally, we explore the use of LLMs in the context of our task. We show how GPT-based models can be used to extract meaningful summaries from the textual data but zero-shot bankruptcy prediction results are poor. All resources required to access and update the dataset or replicate our experiments are available on github.com/henriarnoUG/ECL.
%R 10.18653/v1/2023.finnlp-2.2
%U https://aclanthology.org/2023.finnlp-2.2
%U https://doi.org/10.18653/v1/2023.finnlp-2.2
%P 11-21
Markdown (Informal)
[From Numbers to Words: Multi-Modal Bankruptcy Prediction Using the ECL Dataset](https://aclanthology.org/2023.finnlp-2.2) (Arno et al., FinNLP-WS 2023)
ACL