Deep Learning Based Model for Predicting the Contribution of SMEs to the Economy

Year 2023, , 865 - 874, 01.09.2023

Anıl Utku , Ali Sevinç , M. Ali Akcayol

https://doi.org/10.35234/fumbd.1340992

Abstract

Small and Medium-sized Enterprises (SMEs) are private sector enterprises whose capital, workforce and assets are below the thresholds determined according to national regulations. SMEs play an important role in the economy of most countries in the world, especially in developing countries. SMEs, which make up approximately 90% of enterprises worldwide, provide more than 50% of employment. Estimating the contribution of SMEs to the economy at the country level is very important in terms of planning and investment. In this study, a deep learning-based model was developed to predict the contribution of SMEs to the economy. The developed LSTM-based deep learning model was compared with RF, SVM, CNN, GRU, MLP and RNN. Experimental results showed that the developed model had a better prediction performance than other models compared with 2.169 MSE, 1.473 RMSE, 1.175 MAE, and 0.959 R2 values.

Keywords

SME, MCDM, OCRA, economy, deep learning, machine learning

KOBİ’lerin Ekonomiye Sağladıkları Katkının Tahmini İçin Derin Öğrenme Tabanlı Model

Abstract

Küçük ve Orta Büyüklükteki İşletme (KOBİ)'ler, sermayesi, işgücü ve varlıkları, ulusal yönetmeliklere göre belirlenen eşik değerlerin altında olan özel sektör işletmeleridir. KOBİ'ler, özellikle gelişmekte olan ülkelerde olmak üzere dünyadaki çoğu ülkenin ekonomisinde önemli rol oynamaktadır. Dünya genelinde işletmelerin yaklaşık %90'ını oluşturan KOBİ'ler, istihdamın %50'sinden fazlasını sağlamaktadır. Ülke ölçeğinde KOBİ’lerin ekonomiye katkılarının tahin edilmesi planlama ve yatırım açısından oldukça önemlidir. Bu çalışmada, KOBİ’lerin ekonomiye sağladıkları katkının tahminine yönelik derin öğrenme tabanlı bir model geliştirilmiştir. Geliştirilen LSTM tabanlı derin öğrenme modelinin sonuçları, RF, SVM, CNN, MLP, RNN ve GRU ile karşılaştırılmıştır. Deneysel sonuçlar, geliştirilen derin öğrenme modelinin 2,169 MSE, 1,473 RMSE, 1,175 MAE ve 0,959 R2 değeri ile karşılaştırılan diğer modellerden daha başarılı tahmin performansına sahip olduğunu göstermiştir.

Keywords

KOBİ, ÇKKV, OCRA, ekonomi, derin öğrenme, makine öğrenmesi

References

• Pedraza JM. The micro, small, and medium-sized enterprises and its role in the economic development of a country. Bus and Manag Res 2021; 10(1): 33.
• Naab R, Bans-Akutey A. Assessing the use of e-business strategies by SMEs in Ghana during the Covid-19 pandemic. Ann. Manag and Org. Res 2021; 2(3): 145-160.
• Cegarra‐Leiva D, Sánchez‐Vidal ME, Gabriel Cegarra‐Navarro J. Understanding the link between work life balance practices and organisational outcomes in SMEs: The mediating effect of a supportive culture. Pers rev 2012; 41(3): 359-379.
• Ramírez de la Cruz EE, Grin EJ, Sanabria‐Pulido P, Cravacuore D, Orellana A. The transaction costs of government responses to the COVID‐19 emergency in Latin America. Public Administration Review 2020; 80(4): 683-695.
• Becker W, Schmid O. The right digital strategy for your business: an empirical analysis of the design and implementation of digital strategies in SMEs and LSEs. Bus Res 2020; 13(3): 985-1005.
• Järvenpää AM, Kunttu I, Mäntyneva M. Using foresight to shape future expectations in circular economy SMEs. Tech Inn Man Rev 2020; 10(7).
• Zainudin MF, Adam S, Fuzi NM. The impact of customer buying behavior towards small and medium enterprises (SMEs) perception during pandemic (COVID-19) in Johor. Adv Int J of Bus, Entrepreneurship and SMEs 2021; 10.
• Miklian J, Hoelscher K. SMEs and exogenous shocks: A conceptual literature review and forward research agenda. Int Small Bus J 2022; 40(2): 178-204.
• Vu T, Nguyen D, Luong T, Nguyen T, Doan T. The impact of supply chain financing on SMEs performance in Global supply chain. Unc Supp Ch Man 2022; 10(1): 255-270.
• Matt DT, Rauch E. SME 4.0: The role of small-and medium-sized enterprises in the digital transformation. Ind 4.0 for SMEs: Chal, opp and req 2020; 3-36.
• Bakhtiari S, Breunig R, Magnani L, Zhang J. Financial constraints and small and medium enterprises: A review. Ec Rec 2020; 96(315): 506-523.
• Weaven S, Quach S, Thaichon P, Frazer L, Billot K, Grace D. Surviving an economic downturn: Dynamic capabilities of SMEs. J of Bus Res 2021; 128: 109-123.
• Jayathilaka UR, Park GC. The Impact of Amazon Global Selling on Innovation Performance of SMEs. J of Artif Intell and Mach Lear in Man 2022; 6(2): 1-13.
• Rahman MS, AbdelFattah FA, Bag S, Gani MO. Survival strategies of SMEs amidst the COVID-19 pandemic: application of SEM and fsQCA. J of Bus & Ind Mark 2022; 37(10): 1990-2009.
• Pu G, Qamruzzaman MD, Mehta AM, Naqvi FN, Karim S. Innovative finance, technological adaptation and SMEs sustainability: the mediating role of government support during COVID-19 pandemic. Sust 2021; 13(16): 9218.
• Benzidia S, Makaoui N. Improving SMEs performance through supply chain flexibility and market agility: IT orchestration perspective. Supp Ch Forum: An Int J 2020; 21(3): 173-184.
• Rodríguez-Espíndola O, Cuevas-Romo A, Chowdhury S, Díaz-Acevedo N, Albores P, Despoudi S, Dey P. The role of circular economy principles and sustainable-oriented innovation to enhance social, economic and environmental performance: Evidence from Mexican SMEs. Int J of Prod Econ 2020; 248,
• Mierin LA, Korostyshevskaya EM, Ragimova NSThe Impact of Monopolies on Small Business Development in Russia. Am J Econ Sociol 2019; 78(5): 1201-1228.
• D'Amato D, Veijonaho S, Toppinen A. Towards sustainability? Forest-based circular bioeconomy business models in Finnish SMEs. For Policy Econ 2020; 110: 101848.
• Ezugwu AE, Ikotun AM, Oyelade OO, Abualigah L, Agushaka JO, Eke CI, Akinyelu AA. A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects. Eng App of Artif Int 2022; 110: 104743.
• Confalonieri R, Coba L, Wagner B, Besold TR. A historical perspective of explainable Artificial Intelligence. Wiley Interdiscip Rev Data Min Knowl Discov 2021; 11(1): e1391.
• Aly H. Digital transformation, development and productivity in developing countries: is artificial intelligence a curse or a blessing?. Rev of Econ and Pol Sci 2022; 7(4): 238-256.
• Zhu Y, Zhou L, Xie C, Wang GJ, Nguyen TV. Forecasting SMEs' credit risk in supply chain finance with an enhanced hybrid ensemble machine learning approach. Int J of Prod Econ 2019; 211: 22-33.
• Malakauskas A, Lakštutienė A. Financial distress prediction for small and medium enterprises using machine learning techniques. Eng Econ 2021; 32(1): 4-14.
• Schalck C, Yankol-Schalck M. Predicting French SME failures: new evidence from machine learning techniques. App Econ 2021; 53(51): 5948-5963.
• Hamal S, Senvar Ö. Comparing performances and effectiveness of machine learning classifiers in detecting financial accounting fraud for Turkish SMEs. Int J Comput Intell Syst 2021; 14(1): 769-782.
• Dang C, Wang F, Yang Z, Zhang H, Qian Y. Evaluating and forecasting the risks of small to medium-sized enterprises in the supply chain finance market using blockchain technology and deep learning model. Oper Manag Res 2022; 15(3-4): 662-675.
• Zhang W, Yan S, Li J, Tian X, Yoshida T. Credit risk prediction of SMEs in supply chain finance by fusing demographic and behavioral data. Transp Res E: Logist Transp 2022, 158, 102611.
• Wang L, Jia F, Chen L, Xu Q. Forecasting SMEs’ credit risk in supply chain finance with a sampling strategy based on machine learning techniques. Ann Oper Res 2022, 1-33.
• Zhou X, Lu P, Zheng Z, Tolliver D, Keramati A. Accident prediction accuracy assessment for highway-rail grade crossings using random forest algorithm compared with decision tree. Reliab Eng Syst Saf 2020; 200: 106931.
• Islam MR, Nahiduzzaman M. Complex features extraction with deep learning model for the detection of COVID19 from CT scan images using ensemble based machine learning approach. Expert Syst Appl 2022; 195: 116554.
• Rizwan A, Iqbal N, Ahmad R, Kim DH. WR-SVM model based on the margin radius approach for solving the minimum enclosing ball problem in support vector machine classification. App Sci 2021; 11(10): 4657.
• Sueno HT, Gerardo BD, Medina RP. Multi-class document classification using support vector machine (SVM) based on improved Naïve bayes vectorization technique. Int J Adv Trends Comp Sci Eng 2020; 9(3).
• Sharma AK, Chaurasia S, Srivastava DK. Sentimental short sentences classification by using CNN deep learning model with fine-tuned Word2Vec. Proc Com Sci 2020; 167: 1139-1147.
• Nguyen DT, Nguyen TN, Kim H, Lee HJ. A high-throughput and power-efficient FPGA implementation of YOLO CNN for object detection. IEEE Trans Very Large Scale Integr Syst 2019; 27(8): 1861-1873.
• He T, Li Z, Gong Y, Yao Y, Nie X, Yin Y. Exploring linear feature disentanglement for neural networks. 2022 IEEE International Conference on Multimedia and Expo (ICME), 18-22 June 2022, Taipei, Tayvan, pp. 1-6.
• Djerioui M, Brik Y, Ladjal M, Attallah B. Heart Disease prediction using MLP and LSTM models. 2020 International Conference on Electrical Engineering (ICEE), 25–27 September 2020, Istanbul, Türkiye, pp. 1-5.
• Eskandari H, Imani M, Moghaddam MP. Convolutional and recurrent neural network based model for short-term load forecasting. Electr Power Syst Res 2021; 195: 107173.
• Ismail AA, Gunady M, Pessoa L, Corrada Bravo H, Feizi S. Input-cell attention reduces vanishing saliency of recurrent neural networks. Adv. Neural Inf. Process Syst 2019; 32.
• Wang Y, Zheng D, Jia R. Fault diagnosis method for MMC-HVDC based on Bi-GRU neural network. Energies 2022; 15(3): 994.
• Qin Y, Chen D, Xiang S, Zhu C. Gated dual attention unit neural networks for remaining useful life prediction of rolling bearings. IEEE Trans Ind Inform 2020; 17(9): 6438-6447.
• Ding D, Zhang M, Huang Y, Pan X, Feng F, Jiang E, Yang M. Towards backdoor attack on deep learning based time series classification. 2022 IEEE 38th International Conference on Data Engineering (ICDE), 9-12 May 2022, Kuala Lumpur, Malezya, pp. 1274-1287.
• Bynagari NB. The difficulty of learning long-term dependencies with gradient flow in recurrent nets. Eng Int 2020; 8(2): 127-138.
• Patil S, Mudaliar VM, Kamat P, Gite S. LSTM based Ensemble Network to enhance the learning of long-term dependencies in chatbot. Int J Simul Multidiscip Des Optim 2020; 11: 25.