A Multi-Head LSTM Architecture for Bankruptcy Prediction with Time Series Accounting Data
Future Internet · 27.02.2024 · 16 (3) · 79
DOI: 10.3390/fi16030079 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Internet, online erschienen am 27.02.2024. Verfasst von Mattia Pellegrino und 5 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
With the recent advances in machine learning (ML), several models have been successfully applied to financial and accounting data to predict the likelihood of companies’ bankruptcy. However, time series have received little attention in the literature, with a lack of studies on the application of deep learning sequence models such as Recurrent Neural Networks (RNNs) and the recent Attention-based models in general. In this research work, we investigated the application of Long Short-Term Memory (LSTM) networks to exploit time series of accounting data for bankruptcy prediction. The main contributions of our work are the following: (a) We proposed a multi-head LSTM that models each financial variable in a time window independently and compared it with a single-input LSTM and other traditional ML models. The multi-head LSTM outperformed all the other models. (b) We identified the optimal time series length for bankruptcy prediction to be equal to 4 years of accounting data. (c) We made public the dataset we used for the experiments which includes data from 8262 different public companies in the American stock market generated in the period between 1999 and 2018. Furthermore, we proved the efficacy of the multi-head LSTM model in terms of fewer false positives and the better division of the two classes.
Zitieren
APA
Pellegrino, M., Lombardo, G., Adosoglou, G., Cagnoni, S., Pardalos, P. M., & Poggi, A. (2024). A Multi-Head LSTM Architecture for Bankruptcy Prediction with Time Series Accounting Data. Future Internet, 16(3), 79. https://doi.org/10.3390/fi16030079
Vancouver
Pellegrino M, Lombardo G, Adosoglou G, Cagnoni S, Pardalos PM, Poggi A. A Multi-Head LSTM Architecture for Bankruptcy Prediction with Time Series Accounting Data. Future Internet. 2024;16(3):79. doi:10.3390/fi16030079
BibTeX
@article{Pellegrino2024,
author = {Pellegrino, Mattia and Lombardo, Gianfranco and Adosoglou, George and Cagnoni, Stefano and Pardalos, Panos M. and Poggi, Agostino},
title = {A Multi-Head LSTM Architecture for Bankruptcy Prediction with Time Series Accounting Data},
journal = {Future Internet},
year = {2024},
volume = {16},
number = {3},
pages = {79},
doi = {10.3390/fi16030079}
}
EUVIMED