A Multi-Head LSTM Architecture for Bankruptcy Prediction with Time Series Accounting Data

Mattia Pellegrino, Gianfranco Lombardo, George Adosoglou, Stefano Cagnoni, Panos M. Pardalos and Agostino Poggi ()
Additional contact information
Mattia Pellegrino: Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy
Gianfranco Lombardo: Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy
George Adosoglou: Department of Industrial and Systems Engineering, University of Florida, Gainesville, FL 32611, USA
Stefano Cagnoni: Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy
Panos M. Pardalos: Department of Industrial and Systems Engineering, University of Florida, Gainesville, FL 32611, USA
Agostino Poggi: Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy

Future Internet, 2024, vol. 16, issue 3, 1-20

Abstract: 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.

Keywords: bankruptcy prediction; deep learning; multi-head; Recurrent Neural Networks; stock market (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/16/3/79/pdf (application/pdf)
https://www.mdpi.com/1999-5903/16/3/79/ (text/html)

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:gam:jftint:v:16:y:2024:i:3:p:79-:d:1346609

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().