GALSTM-FDP: A Time-Series Modeling Approach Using Hybrid GA and LSTM for Financial Distress Prediction

被引:6
|
作者
Al Ali, Amal [1 ]
Khedr, Ahmed M. [2 ,3 ]
El Bannany, Magdi [4 ,5 ]
Kanakkayil, Sakeena [2 ]
机构
[1] Univ Sharjah, Informat Syst Dept, Sharjah 27272, U Arab Emirates
[2] Univ Sharjah, Comp Sci Dept, Sharjah 27272, U Arab Emirates
[3] Zagazig Univ, Math Dept, Zagazig 44519, Egypt
[4] Umm Al Quwain Univ, Coll Business Adm, Umm Al Quwain 536, U Arab Emirates
[5] Ain Shams Univ, Fac Business, Dept Accounting & Auditing, Cairo 11566, Egypt
来源
关键词
financial distress prediction (FDP); long short term memory (LSTM); genetic algorithm (GA); machine learning (ML); GENETIC ALGORITHM; RATIOS; MARKET; BANKS;
D O I
10.3390/ijfs11010038
中图分类号
F8 [财政、金融];
学科分类号
0202 ;
摘要
Despite the obvious benefits and growing popularity of Machine Learning (ML) technology, there are still concerns regarding its ability to provide Financial Distress Prediction (FDP). An accurate FDP model is required to avoid financial risk at the lowest possible cost. However, in the Internet era, financial data are exploding, and they are being coupled with other kinds of risk data, making an FDP model challenging to operate. As a result, researchers presented several novel FDP models based on ML and Deep Learning. Time series data is are important to reflect the multi-source and heterogeneous aspects of financial data. This paper gives insight into building a time-series model and forecasting distress far in advance of its occurrence. To build an efficient FDP model, we provide a hybrid model (GALSTM-FDP) that incorporates LSTM and GA. Unlike other previous studies, which established models that predicted distress probability only within one year, our approach predicts distress two years ahead. This research integrates GA with LSTM to find the optimum hyperparameter configuration for LSTM. Using GA, we focus on optimizing architectural aspects for modeling the optimal network based on prediction accuracy. The results showed that our algorithm outperforms other state-of-the-art methods in terms of predictive accuracy.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Time-Series Forecasting Using SVMD-LSTM: A Hybrid Approach for Stock Market Prediction
    Agarwal, Sanskar
    Sharma, Shivam
    Faisal, Kazi Newaj
    Sharma, Rishi Raj
    JOURNAL OF PROBABILITY AND STATISTICS, 2025, 2025 (01)
  • [2] A Hybrid Approach for Modeling Financial Time Series
    Barbulescu, Alina
    Bautu, Elena
    INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, 2012, 9 (04) : 327 - 335
  • [3] Multivariate Time-Series Prediction Using LSTM Neural Networks
    Ghanbari, Reza
    Borna, Keivan
    2021 26TH INTERNATIONAL COMPUTER CONFERENCE, COMPUTER SOCIETY OF IRAN (CSICC), 2021,
  • [4] Multivariate CNN-LSTM Model for Multiple Parallel Financial Time-Series Prediction
    Widiputra, Harya
    Mailangkay, Adele
    Gautama, Elliana
    COMPLEXITY, 2021, 2021
  • [5] Financial Time-Series Prediction by Fusing Dual-Pathway Attention with VT-LSTM
    Dai, Yurui
    An, Junxiu
    Tao, Quanhui
    Computer Engineering and Applications, 2023, 59 (12) : 157 - 165
  • [6] ADAPTIVE PREDICTION OF FINANCIAL TIME-SERIES FOR DECISION-MAKING USING A TENSORIAL AGGREGATION APPROACH
    Campello, Betania S. C.
    Duarte, Leonardo T.
    Romano, Joao M. T.
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 5435 - 5439
  • [7] Time-series prediction of hourly atmospheric pressure using ANFIS and LSTM approaches
    Mehmet Bilgili
    Akın Ilhan
    Şaban Ünal
    Neural Computing and Applications, 2022, 34 : 15633 - 15648
  • [8] Time-series prediction of hourly atmospheric pressure using ANFIS and LSTM approaches
    Bilgili, Mehmet
    Ilhan, Akin
    Unal, Saban
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (18): : 15633 - 15648
  • [9] Financial time series prediction using neurofuzzy approach
    Liu Jianguo
    Wu Weiping
    Advanced Computer Technology, New Education, Proceedings, 2007, : 121 - 124
  • [10] Online QoS Prediction in the Cloud Environments Using Hybrid Time-Series Data Mining Approach
    Keshavarzi, Amin
    Toroghi Haghighat, Abolfazl
    Bohlouli, Mahdi
    IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF ELECTRICAL ENGINEERING, 2021, 45 (02) : 461 - 478