Corporate risk stratification through an interpretable autoencoder-based model

被引:0
作者
Giuliani, Alessandro [1 ]
Savona, Roberto [2 ]
Carta, Salvatore [1 ]
Addari, Gianmarco [3 ]
Podda, Alessandro Sebastian [1 ]
机构
[1] Univ Cagliari, Dept Math & Comp Sci, Palazzo Sci,Via Osped 72, I-09124 Cagliari, Italy
[2] Univ Brescia, Dept Econ & Management, Via San Faustino 74-B, I-25122 Brescia, Italy
[3] VisioScientiae Srl, Via San Tommaso Aquino 20, I-09134 Cagliari, Italy
关键词
Deep learning; Autoencoder; Balance sheets; Corporate risk; Financial sustainability; FINANCIAL RATIOS; PREDICTION;
D O I
10.1016/j.cor.2024.106884
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
In this manuscript, we propose an innovative early warning Machine Learning-based model to identify potential threats to financial sustainability for non-financial companies. Unlike most state-of-the-art tools, whose outcomes are often difficult to understand even for experts, our model provides an easily interpretable visualization of balance sheets, projecting each company in a bi-dimensional space according to an autoencoder-based dimensionality reduction matched with a Nearest-Neighbor-based default density estimation. In the resulting space, the distress zones, where the default intensity is high, appear as homogeneous clusters directly identified. Our empirical experiments provide evidence of the interpretability, forecasting ability, and robustness of the bi-dimensional space.
引用
收藏
页数:16
相关论文
共 50 条
[41]   Autoencoder-based IDS for cloud and mobile devices [J].
Faber, Kamil ;
Faber, Lukasz ;
Sniezynski, Bartlomiej .
21ST IEEE/ACM INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND INTERNET COMPUTING (CCGRID 2021), 2021, :728-736
[42]   Autoencoder-based Metamodeling for Structural Design Optimization [J].
Schneider, Fabian ;
Hellmig, Ralph J. ;
Nelles, Oliver .
IFAC PAPERSONLINE, 2024, 58 (28) :288-293
[43]   Astral: An Autoencoder-Based Model for Pedestrian Trajectory Prediction of Variable-Length [J].
Diao, Yupeng ;
Su, Yiteng ;
Zeng, Ximu ;
Chen, Xu ;
Liu, Shuncheng ;
Su, Han .
DATABASE SYSTEMS FOR ADVANCED APPLICATIONS. DASFAA 2022 INTERNATIONAL WORKSHOPS, 2022, 13248 :214-228
[44]   Autoencoder-based OFDM for Agricultural Image Transmission [J].
Li, Dongbo ;
Liu, Xiangyu ;
Shao, Yuxuan ;
Sun, Yuchen ;
Cheng, Siyao ;
Liu, Jie .
2022 TENTH INTERNATIONAL CONFERENCE ON ADVANCED CLOUD AND BIG DATA, CBD, 2022, :157-162
[45]   A Deep Autoencoder-Based Hybrid Recommender System [J].
Bougteb, Yahya ;
Ouhbi, Brahim ;
Frikh, Bouchra ;
Zemmouri, Elmoukhtar .
INTERNATIONAL JOURNAL OF MOBILE COMPUTING AND MULTIMEDIA COMMUNICATIONS, 2022, 13 (01)
[46]   TWO-STREAM AUTOENCODER-BASED HYPERSPECTRAL UNMIXING USING HAPKE MODEL [J].
Li, Ruihua ;
Liu, Hongyi ;
Zhang, Jun ;
Wei, Zhihui .
2024 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2024), 2024, :9434-9437
[47]   A hybrid model of CNN and LSTM autoencoder-based short-term PV power generation forecasting [J].
Ibrahim, Mohamed Sayed ;
Gharghory, Sawsan Morkos ;
Kamal, Hanan Ahmed .
ELECTRICAL ENGINEERING, 2024, 106 (04) :4239-4255
[48]   Autoencoder-Based Restoration of Multi-Channel Sensor Signal Loss [J].
Lee, Jaejun ;
Seo, Hogeon ;
Yu, Yonggyun .
JOURNAL OF THE KOREAN SOCIETY FOR NONDESTRUCTIVE TESTING, 2024, 44 (03) :213-218
[49]   Deep autoencoder-based fuzzy c-means for topic detection [J].
Murfi, Hendri ;
Rosaline, Natasha ;
Hariadi, Nora .
ARRAY, 2022, 13
[50]   Autoencoder-based detection of near-surface defects in ultrasonic testing [J].
Ha, Jong Moon ;
Seung, Hong Min ;
Choi, Wonjae .
ULTRASONICS, 2022, 119