Comparison of artificial neural networks learning methods to evaluate supply chain performance

Abstract

The supply chain performance evaluation is a critical activity to continuously improve operations. Literature presents several performance evaluation systems based on multi-criteria methods and artificial intelligence. Among them, the systems based on artificial neural networks (ANN) excel due to their capacity of modeling non-linear relationships between metrics and allowing adaptations to a specific environment by means of historical performance data. These systems’ accuracy depend directly on the adopted training algorithm, and no studies have been found that assess the efficiency of these algorithms when applied to supply chain performance evaluation. In this context, the present study evaluates four ANNs learning methods in order to investigate which one is the most adequate to deal with supply chain evaluation. The algorithms tested were Gradient Descendent Momentum, Levenberg-Marquardt, Quasi-Newton and Scale Conjugate Gradient. The performance metrics were extracted from SCOR®, which is a reference model used worldwide. The random sub-sampling cross-validation method was adopted to find the most adequate topological configuration for each model. A set of 80 topologies was implemented using MATLAB®. The prediction accuracy evaluation was based on the mean square error. For the four level 1 metrics considered, the Levenberg-Marquardt algorithm provided the most precise results. The results of correlation analysis and hypothesis tests reinforce the accuracy of the proposed models. Furthermore, the proposed computational models reached a prediction accuracy higher than previous approaches.

Data Analytics in Supply Chain Management: A State-of-the-Art Literature Review

“…In addition to the former topics of risk management (Kara et al, 2020;Melançon et al, 2021;Dai & Liu, 2020;Salamai et al, 2021;Jing Wu et al, 2022), sustainability and green supply chain (Gholizadeh et al, 2020;D. Ma et al, 2021;Wong et al, 2021;Abdella et al, 2020;Goodarzian et al, 2021;Moghimi & Beheshtinia, 2021;Nagendra et al, 2020;Kuo et al, 2021;Park, 2021), and performance management (Jiang et al 2021b;Chakraborty and Das, 2021;Li et al 2020c;Lunardi and Lima Junior, 2021;Abdelsamad et al, 2021). Supply chain collaboration and integration (Ali et al, 2021a;Gumte et al, 2021;Guillermo Muñoz et al, 2020;Xiang, 2020), supply chain network design (Zhou and Guo, 2021;Yang et al, 2021d) and transparency and traceability (Wong et al, 2021;Ping Zhang et al, 2021;Khan et al, 2020) have been discussed in recent DA publications.…”

“…,Gholizadeh et al (2020),Bifulco et al (2021),Yu et al (2021b),Jiang et al (2021b),,Ma et al (2021a),Li and Mao (2020),Deng et al (2020),Bertsimas and Kallus (2020),Goodarzian et al (2021),Chakraborty and Das (2021),Ali et al. (2021a),Moghimi and Beheshtinia (2021),Dai and Liu (2020),Li et al (2020c),Abdella et al (2020),Wong et al (2021),Kuo et al (2021), Narwane et al (2021,Zhou and Guo (2021),Salamai et al (2021), Park (2021),Wu et al (2022),Asghari et al (2021),Fang and Su (2021),Gumte et al (2021), Yeboah-Ofori et al (2021,Wan (2021), Ping, Huang (2021), Guillermo Muñoz et al (2020),Lunardi and Lima Junior (2021),Xiang (2020),Khan et al (2020),Sang (2021), Jianying et al ( 2021), Abdelsamad et al (2021), Nezamoddini et al (2020), Abdelaziz et al (2020), Yang et al (2021d), Akbarian-Saravi et al (2020), Chen et al (2021a) Logistics Intelligent transportation system Dimokas et al (2020), Ibrahim et al (2020), Chen et al (2021b), Hwang (2021), Lorenc et al (2021), Wiegmans et al (2020), Mouammine et al(2020), Zanin et al (2020), Cerquitelli et al (2020), TASHEV et al (2020), Zhang et al (2020b), Kinra et al (2020), George and Santra (2020), Gupta et al (2020), Chen (2020), Ding (2020), Kosowska-Stamirowska (2020), Harrison et al (2020), Chen et al (2021c), Han et al (2021a), Sarabia-Jácome et al (2019), Lock et al (2021), Tsolakis et al (2021), Jurdana et al (2020), Oucheikh et al (2021), Lee and Jeong (2021), Adi et al (2020), Ren et al (2020), Nadi et al (2021) In-transit inventory management Li et al (2020b), Sun et al (2020b), Yi and Ma (2020), Li and He (2021), Kim et al (2020a), Molaris et al (2021) Logistics planning Moscoso-López et al (2021), Balster et al (2020), Liang and Wang (2021), Mangina et al (2020), Cheng and Pan (2021), Choi (2020), Yue et al (2021), Monteil et al (2021), Vorkapić et al (2021), Hathikal et al (2020), Wang and Y...…”