Hybrid Deep Learning Model for Predicting the Contribution of SMEs to the Economy: A Case Study for Turkey

Year 2025, Volume: 6 Issue: 2, 1 - 19

Anıl Utku , Ali Sevinç , M. Ali Akcayol

https://doi.org/10.55195/jscai.1757092

Abstract

In this study, a combination of deep learning models was developed to calculate the economic contribution of SMEs. The hybrid model's advantage lies in its ability to leverage the strengths of CNN to identify spatial relationships and draw patterns, as well as LSTM to capture sequential temporal dependencies. The goal of this hybrid model was to provide an accurate estimate of the economic contribution of SMEs. To compare the effectiveness of the hybrid model, extensive comparative experiments were conducted using a dataset of economic indicators of SMEs in Tadrakea. The experiments demonstrated that CNN-LSTM outperforms other commonly used machine learning and deep learning networks. A hybrid model, combining CNN and LSTM, can be used to capture complex data, thereby improving prediction accuracy.

Keywords

SME , Economy , Deep learning , Machine learning

References

• F. Manzoor, L. Wei ve M. Siraj, “Small and medium-sized enterprises and economic growth in Pakistan: An ARDL bounds cointegration approach”, Heliyon, c. 7, sy 2, 2021.
• S. Benzidia ve N. Makaoui, “Improving SMEs performance through supply chain flexibility and market agility: IT orchestration perspective”, Supply chain forum: An international journal, c. 21, sy 3, ss. 173-184, 2020.
• L. Westman, E. Moores ve S. L. Burch, “Bridging the governance divide: The role of SMEs in urban sustainability interventions”, Cities, c. 108, 2021.
• T. Hai Thi Thanh ve V. N. Tron, “The Differential Effects of Government Support, Inter-Firm Collaboration, and Firm Financial Resources on SME Performance in Vietnam”, Cuadernos de Economía, c. 46, sy 130, ss. 124-134, 2023.
• H. Li, Y. Jiang, A. Ashiq, A. Salman, M. Haseeb ve M. S. Shabbir, “The role of technological innovation, strategy, firm’s performance, and firm’s size and their aggregate impact on organizational structure”, Managerial and Decision Economics, c. 44, sy 4, ss. 2010-2020, 2023.
• C. E. De Marco, I. Martelli ve A. Di Minin, “European SMEs’ engagement in open innovation When the important thing is to win and not just to participate, what should innovation policy do?”, Technological Forecasting and Social Change, c. 152, 2020.
• M. Dabić, N. Stojčić, M. Simić, V. Potocan, M. Slavković ve Z. Nedelko, “Intellectual agility and innovation in micro and small businesses: The mediating role of entrepreneurial leadership”, Journal of Business Research, c. 123, ss. 683-695, 2021.
• A. Sircar, K. Yadav, K. Rayavarapu, N. Bist ve H. Oza, “Application of machine learning and artificial intelligence in oil and gas industry”, Petroleum Research, c. 6, sy 4, ss. 379-391, 2021.
• G. Lăzăroiu, M. Andronie, M. Iatagan, M. Geamănu, R. Ștefănescu ve I. Dijmărescu, “Deep learning-assisted smart process planning, robotic wireless sensor networks, and geospatial big data management algorithms in the internet of manufacturing things”, ISPRS International Journal of Geo-Information, c. 11, sy 5, 2022.
• J. P. Bharadiya, “Leveraging Machine Learning for Enhanced Business Intelligence”, International Journal of Computer Science and Technology, c. 7, sy 1, ss. 1-19, 2023.
• L. Crosato, C. Liberati ve M. Repetto, “Lost in a black‐box? Interpretable machine learning for assessing Italian SMEs default”, Applied Stochastic Models in Business and Industry, 2023.
• A. Angelopoulos, E. T. Michailidis, N. Nomikos, P. Trakadas, A. Hatziefremidis, S. Voliotis ve T. Zahariadis, “Tackling faults in the industry 4.0 era—a survey of machine-learning solutions and key aspects”, Sensors, c. 20, sy 1, 2019.
• M. Shehab, L. Abualigah, Q. Shambour, M. A. Abu-Hashem, M. K. Y. Shambour, A. I. Alsalibi ve A. H. Gandomi, “Machine learning in medical applications: A review of state-of-the-art methods”, Computers in Biology and Medicine, c. 145, 2022.
• O. Adeola, P. Gyimah, K. O. Appiah ve R. N. Lussier, “Can critical success factors of small businesses in emerging markets advance UN Sustainable Development Goals?”, World Journal of Entrepreneurship, Management and Sustainable Development, c. 17, sy 1, ss. 85-105, 2021.
• F. Liu, X. Zhou, J. Cao, Z. Wang, T. Wang, H. Wang ve Y. Zhang, “Anomaly detection in quasi-periodic time series based on automatic data segmentation and attentional LSTM-CNN”, IEEE Transactions on Knowledge and Data Engineering, c. 34, sy 6, ss. 2626-2640, 2020.
• K. M. Rashid ve J. Louis, “Times-series data augmentation and deep learning for construction equipment activity recognition”, Advanced Engineering Informatics, c. 42, 2019.
• Y. Luan ve S. Lin, “Research on text classification based on CNN and LSTM”, 2019 IEEE international conference on artificial intelligence and computer applications (ICAICA), ss. 352-355, 2019.
• F. Aksan, V. Suresh, P. Janik ve T. Sikorski, “Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning Models”, Energies, c. 16, sy 14, 2023.
• I. Afolabi, T. C. Ifunaya, F. G. Ojo ve C. Moses, “A model for business success prediction using machine learning algorithms”, In Journal of Physics: Conference Series, c. 1299, sy 1, 2019.
• A. Belhadi, S. S. Kamble, V. Mani, I. Benkhati ve F. E. Touriki, “An ensemble machine learning approach for forecasting credit risk of agricultural SMEs’ investments in agriculture 4.0 through supply chain finance”, Annals of Operations Research, ss. 1-29, 2021.
• G. Kou, Y. Xu, Y. Peng, F. Shen, Y. Chen, K. Chang ve S. Kou, “Bankruptcy prediction for SMEs using transactional data and two-stage multi-objective feature selection”, Decision Support Systems, c. 140, 2021.
• S. Hamal ve Ö. Senvar, “Comparing performances and effectiveness of machine learning classifiers in detecting financial accounting fraud for Turkish SMEs”, Int. J. Comput. Intell. Syst., c. 14, sy 1, ss. 769-782, 2021.
• L. Wang, F. Jia, L. Chen ve Q. Xu, “Forecasting SMEs’ credit risk in supply chain finance with a sampling strategy based on machine learning techniques”, Annals of Operations Research, ss. 1-33, 2022.
• W. Zhang, S. Yan, J. Li, X. Tian ve T. Yoshida, “Credit risk prediction of SMEs in supply chain finance by fusing demographic and behavioral data”, Transportation Research Part E: Logistics and Transportation Review, c. 158, 2022.
• W. Zhang, G. Cui, Y. Wang, C. Zheng ve Q. Zhu, “A human comfort prediction method for indoor personnel based on time-series analysis. In Building Simulation, c. 16, sy 7, ss. 1187-1201, 2023.
• T. Zhu, C. Luo, Z. Zhang, J. Li, S. Ren ve Y. Zeng, “Minority oversampling for imbalanced time series classification”, Knowledge-Based Systems, c. 247, 2022.
• D. Maulud ve A. M. Abdulazeez, “A review on linear regression comprehensive in machine learning”, Journal of Applied Science and Technology Trends, c. 1, sy 4, ss. 140-147, 2020.
• V. E. Sathishkumar, A. G. Ramu ve J. Cho, “Machine learning algorithms to predict the catalytic reduction performance of eco-toxic nitrophenols and azo dyes contaminants”, Alexandria Engineering Journal, c. 72, ss. 673-693, 2023.
• Z. Hu, Y. Zhao ve M. Khushi, “A survey of forex and stock price prediction using deep learning”, Applied System Innovation, c. 4, sy 1, 2021.
• C. H. Chen, K. Tanaka, M. Kotera ve K. Funatsu, “Comparison and improvement of the predictability and interpretability with ensemble learning models in QSPR applications”, Journal of cheminformatics, c. 12, ss. 1-16, 2020.
• N. J. Fai, W. K. Wey, K. Y. Qi, G. J. Xian, R. J. M. Chun ve Z. A. bin Abdul Salam, “Digits Classification Using Random Forest Classifier”, Journal of Applied Technology and Innovation, c. 7, sy 3, 2023.
• Z. Amiri, A. Heidari, N. J. Navimipour, M. Unal ve A. Mousavi, “Adventures in data analysis: A systematic review of Deep Learning techniques for pattern recognition in cyber-physical-social systems”, Multimedia Tools and Applications, ss. 1-65, 2023.
• Y. Liu, “Novel volatility forecasting using deep learning–long short term memory recurrent neural networks”, Expert Systems with Applications, c. 132, ss. 99-109, 2019.
• X. Yan, “Research on Financial Field Integrating Artificial Intelligence: Application Basis, Case Analysis, and SVR Model-Based Overnight”, Applied Artificial Intelligence, c. 37, sy 1, 2023.
• S. N. Khan, S. U. Khan, H. Aznaoui, C. B. Şahin ve Ö. B. Dinler, “Generalization of linear and non-linear support vector machine in multiple fields: a review”, Computer Science and Information Technologies, c. 4, sy 3, ss. 226-239, 2023.
• M. Ehtearm, H. Ghayoumi Zadeh, A. Seifi, A. Fayazi ve M. Dehghani, “Predicting hydropower production using deep learning CNN-ANN hybridized with gaussian process regression and salp algorithm”, Water Resources Management, c. 37, sy 9, ss. 3671-3697, 2023.
• B. Dou, Z. Zhu, E. Merkurjev, L. Ke, L. Chen, J. Jiang ve G. W. Wei, “Machine Learning Methods for Small Data Challenges in Molecular Science”, Chemical Reviews, c. 123, sy 13, ss. 8736-8780, 2023.
• R. Wang, Q. Guo, S. Lu ve C. Zhang, “Tire defect detection using fully convolutional network”, IEEE Access, c. 7, ss. 43502-43510, 2019.
• Q. Zhang, N. Fragnito, X. Bao ve N. Sharma, “A deep learning method to predict ankle joint moment during walking at different speeds with ultrasound imaging: A framework for assistive devices control”, Wearable Technologies, c. 3, 2022.
• Y. He, P. Huang, W. Hong, Q. Luo, L. Li ve K. L. Tsui, “In-depth insights into the application of Recurrent Neural Networks (RNNs) in traffic prediction: A comprehensive review”, Algorithms, c. 17, sy 9, 2024.
• J. P. Bharadiya, “Exploring the Use of Recurrent Neural Networks for Time Series Forecasting”, International Journal of Innovative Science and Research Technology, c. 8, sy 5, ss. 2023-2027, 2023.
• Y. Ren, D. Zhao, D. Luo, H. Ma ve P. Duan, “Global-local temporal convolutional network for traffic flow prediction”, IEEE Transactions on Intelligent Transportation Systems, c. 23, sy 2, ss. 1578-1584, 2020.
• D. M. Belete ve M. D. Huchaiah, “Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results”, International Journal of Computers and Applications, c. 44, sy 9, ss. 875-886, 2022.
• Y. W. Chen, Q. Song ve X. Hu, “Techniques for automated machine learning”, ACM SIGKDD Explorations Newsletter, c. 22, sy 2, ss. 35-50, 2021.