A hybrid DEA-BPNN framework for performance modelling of Indonesian listed furniture and wood processing firms

Zain Amarta; Niki Etruly; Julia Dewi Ma'rifah

doi:10.24123/mabis.v25i2.1113

A hybrid DEA-BPNN framework for performance modelling of Indonesian listed furniture and wood processing firms

Zain Amarta^(1*), Niki Etruly⁽²⁾, Julia Dewi Ma'rifah⁽³⁾,

(1) Furniture and Wood Processing Industry Polytechnic
(2) Furniture and Wood Processing Industry Polytechnic
(3) Furniture and Wood Processing Industry Polytechnic
(*) Corresponding Author

Abstract

This study proposes a hybrid Data Envelopment Analysis-Backpropagation Neural Network (DEA-BPNN) framework to evaluate and predict the efficiency performance of furniture and wood processing firms listed on the Indonesia Stock Exchange (IDX). As a strategic manufacturing sector, firm performance in this industry is frequently challenged by cost volatility, scale inefficiencies, and fluctuating market demand, while conventional efficiency methods remain limited in capturing nonlinear relationships and predictive insights. To address these limitations, the study integrates frontier-based efficiency measurement with machine learning-based prediction. Using panel data from six IDX-listed firms over the 2020-2024 period, efficiency scores are first estimated through CCR and BCC DEA models, with total assets, cost of goods sold, and operating expenses as inputs, and revenue and profit as outputs. The results reveal notable heterogeneity in efficiency performance, where several firms achieve full BCC efficiency, indicating strong pure technical efficiency, while variations in CCR efficiency highlight the presence of scale inefficiencies. In the second stage, a BPNN model is developed to predict CCR and BCC efficiency scores. The optimized 5-8-2 network architecture demonstrates strong predictive performance, achieving a Mean Squared Error (MSE) of 0.0145, low Mean Absolute Percentage Error (MAPE) values of 1.22% (CCR) and 0.89% (BCC), and high Pearson correlation coefficients of 0.94 and 0.96. Overall, the findings confirm that the hybrid DEA-BPNN framework provides a robust tool for efficiency evaluation and prediction, supporting performance monitoring and strategic decision-making in Indonesia’s furniture and wood processing industry.

Keywords

Performance modelling; DEA; BPNN; Furniture; Wood processing

Full Text:

PDF

References

Abbasimehr, H., Shabani, M., & Yousefi, M. (2020). An optimized model using LSTM network for demand forecasting. Computers and Industrial Engineering, 143, 106435. https://doi.org/10.1016/j.cie.2020.106435

Abdullah, A., Saraswat, S., & Talib, F. (2023). Impact of Smart, Green, Resilient, and Lean Manufacturing System on SMEs’Performance: A Data Envelopment Analysis (DEA) Approach. Sustainability, 15(2), 1379. https://doi.org/10.3390/su15021379

Akbal, B. (2018). GSA-ANN and DEA-ANN Methods to Prevent Underground Cable Line Faults. International Journal of Computer and Electrical Engineering, 10(2), 85–93. https://doi.org/10.17706/IJCEE.2018.10.2.85-93

Akgöbek, Ö., & Yakut, E. (2014). Efficiency measurement in Turkish manufacturing sector using Data Envelopment Analysis (DEA) and Artificial Neural Networks (ANN). Journal of Economic & Financial Studies, 2(03), 35–45. https://doi.org/10.18533/jefs.v2i02.138

Amarta, Z., & Ma’rifah, J. D. (2021). Peramalan penjualan produk furniture dengan metode backpropagation neural network. Jurnal Ilmiah Teknik Industri, 9(1), 29–35. https://doi.org/10.24912/jitiuntar.v9i1.9510

Amarta, Z., Soepangkat, B. O. P., Sutikno, & Norcahyo, R. (2019). Multi response optimization in vulcanization process using backpropagation neural network-genetic algorithm method for reducing quality loss cost. AIP Conference Proceedings, 2114, 020003. https://doi.org/10.1063/1.5112387

Anamika, Kumar, N., & Akella, A. K. (2014). Prediction and Efficiency Evaluation of Solar Energy Resources by using mixed ANN and DEA Approaches. International Conference on Advances in Computing, Communications and Informatics (ICACCI), 774. https://doi.org/10.1109/ICACCI.2014.6968588

Azadeh, A., Roohani, A., & Haghighi, S. M. (2015). Performance optimization of gas refineries by ANN and DEA based on financial and operational factors. World Journal of Engineering, 12(2), 109–134. https://doi.org/10.1260/1708-5284.12.2.109

Bibaud-Alves, J., Thomas, P., & Haouzi, H. B. El. (2019). Demand forecasting using artificial neuronal networks and time series: application to a French furniture manufacturer case study. 11th International Joint Conference on Computatiional Intelligence IJCCI’19. https://doi.org/hal.science/hal-02304581v1

Fri, M., Douaioui, K., Tetouani, S., Mabrouki, C., & Semma, E. A. (2020). A DEA-ANN framework based in Improved Grey Wolf Algorithm to evaluate the performance of container terminal. IOP Conference Series: Materials Science and Engineering, 827(1), 012040. https://doi.org/10.1088/1757-899X/827/1/012040

Jauhar, S. K., Zolfagharinia, H., & Amin, S. H. (2023). A DEA-ANN-based analytical framework to assess and predict the efficiency of Canadian universities in a service supply chain context. Benchmarking: An International Journal, 30(8), 2734–2782. https://doi.org/10.1108/BIJ-08-2021-0458

Kahi, V. S., Yousefi, S., Shabanpour, H., & Saen, R. F. (2017). How to evaluate sustainability of supply chains? A dynamic network DEA approach. Industrial Management and Data Systems, 117(9), 1866–1889. https://doi.org/10.1108/IMDS-09-2016-0389

Krišt’Aková, S., Neykov, N., Antov, P., Sedliačiková, M., Reh, R., Halalisan, A. F., & Hajdúchová, I. (2021). Efficiency of Wood-Processing Enterprises—Evaluation Based on DEA and MPI: A Comparison between Slovakia and Bulgaria for the Period 2014–2018. Forests, 12(8), 1026. https://doi.org/10.3390/f12081026

Kropivšek, J., & Grošelj, P. (2019). Long-term financial analysis of the Slovenian wood industry using dea. Drvna Industrija, 70(1), 61–70. https://doi.org/10.5552/drvind.2019.1810

Kwon, H. B. (2014). Performance modeling of mobile phone providers: A DEA-ANN combined approach. Benchmarking: An International Journal, 21(6), 1120–1144. https://doi.org/10.1108/BIJ-01-2013-0016

Kwon, H. B. (2017). Exploring the predictive potential of artificial neural networks in conjunction with DEA in railroad performance modeling. International Journal of Production Economics, 183, 159–170. https://doi.org/10.1016/j.ijpe.2016.10.022

Kwon, H. B., Lee, J., & Roh, J. J. (2016). Best performance modeling using complementary DEA-ANN approach: Application to Japanese electronics manufacturing firms. Benchmarking: An International Journal, 23(3), 704–721. https://doi.org/10.1108/BIJ-09-2014-0083

Kwon, H. B., Marvel, J. H., & Roh, J. J. (2017). Three-stage performance modeling using DEA–BPNN for better practice benchmarking. Expert Systems with Applications, 71, 429–441. https://doi.org/10.1016/j.eswa.2016.11.009

Lazarević, A., Glavonjić, B., Oblak, L., Kalem, M., & Čomić, D. (2022). Analysis of Operational Efficiency of Wooden Chair Manufacturing Companies in Serbia using DEA. Drvna Industrija, 73(1), 81–90. https://doi.org/10.5552/drvind.2022.2136

Neykov, N., Sedliacikova, M., Antov, P., Potkány, M., Kitchoukov, E., Halalisan, A. F., & Poláková, N. (2024). Efficiency of Micro and Small Wood-Processing Enterprises in the EU—Evidence from DEA and Fractional Regression Analysis. Forests, 15(1), 58. https://doi.org/10.3390/f15010058

Olanrewaju, O. A. (2021). Integrated index decomposition analysis-artificial neural network-data envelopment analysis (IDA-ANN-DEA): implementation guide. Energy Efficiency, 14(7), 71. https://doi.org/10.1007/s12053-021-09990-9

Park, S., & Kim, J. (2016). Energy efficiency in Korea: analysis using a hybrid DEA model. Geosystem Engineering, 19(3), 143–150. https://doi.org/10.1080/12269328.2016.1154485

Ratner, S. V., Shaposhnikov, A. M., & Lychev, A. V. (2023). Network DEA and Its Applications (2017–2022): A Systematic Literature Review. In Mathematics (Vol. 11, Number 9, p. 2141). MDPI. https://doi.org/10.3390/math11092141

Sedliačiková, M., Neykov, N., Dobrovič, J., Šatanová, A., Osvaldová, M., & Palinchak, M. (2024). Performance measuring of wood-processing microenterprises through Data Envelopment Analysis: A case study of Slovakia, Poland, and Bulgaria. Entrepreneurship and Sustainability Issues, 11(3), 408–422. https://doi.org/10.9770/jesi.2024.11.3(28)

Shi, Y., Yu, A., Higgins, H. N., & Zhu, J. (2021). Shared and unsplittable performance links in network DEA. Annals of Operations Research, 303(1–2), 507–528. https://doi.org/10.1007/s10479-020-03882-4

Singh, N., & Pant, M. (2018). Evaluating the Efficiency of Higher Secondary Education State Boards in India: A DEA-ANN Approach. Advances in Intelligent Systems and Computing, 736, 942–951. https://doi.org/10.1007/978-3-319-76348-4_90

Suryanita, R., Maizir, H., Firzal, Y., Jingga, H., & Yuniarto, E. (2019). Response prediction of multi-story building using backpropagation neural networks method. MATEC Web of Conferences, 276, 01011. https://doi.org/10.1051/matecconf/201927601011

Tsolas, I. E., Charles, V., & Gherman, T. (2020). Supporting better practice benchmarking: A DEA-ANN approach to bank branch performance assessment. Expert Systems with Applications, 160, 113599. https://doi.org/10.1016/j.eswa.2020.113599

Zhang, Z., Xiao, Y., & Niu, H. (2022). DEA and Machine Learning for Performance Prediction. Mathematics, 10(10), 1776. https://doi.org/10.3390/math10101776

Zhu, N., Zhu, C., & Emrouznejad, A. (2021). A combined machine learning algorithms and DEA method for measuring and predicting the efficiency of Chinese manufacturing listed companies. Journal of Management Science and Engineering, 6(4), 435–448. https://doi.org/10.1016/j.jmse.2020.10.001

DOI: https://doi.org/10.24123/mabis.v25i2.1113

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

There are currently no refbacks.

This work is licensed under a Creative Commons Attribution 4.0 International License.

This work is licensed under a Creative Commons Attribution 4.0 International License. ISSN: 1412-3789. e-ISSN: 2477-1783.

Username
Password
Remember me