models are not perfect, they can be used in the prediction of suppliers’ learning behavior, and they can provide insights on the relationship between the learning behaviors and suppliers’
characteristics.
Furthermore, to see the performance difference, binary classification models are also tried to see if the model performance enhances in different topics. The binary classification model is obtained by creating 4 different models per each topic and overall sustainability score. For ex-ample, the first model considers the classification task between fast learners with other learning behaviors whereas the model with sustainability learning behaviors considers the classification between slow learners with other learning behaviors and so on. To compare the performance of models, the average AUC values are calculated for binary classification models per each topic and overall sustainability score. Table 12 represents a comparison of AUC values between binary and multi-class classification models.
Table 12: Comparison of performances between binary and multi-class models
One can look at Table 12 to compare model performances. This comparison demonstrates that the model with multi-class classification performs better than the model with binary classi-fication for each topic and overall sustainability score. Therefore, the detailed analysis to see which characteristics influence which learning behavior is performed with the multi-class clas-sification models.
3.3 Results
The models are obtained by eliminating some of the independent variables using the feature selection algorithm and using dependent variables as learning behaviors.For explaining the models and the influence of independent variables on the dependent variable, SHAP values are explained. It provides insights on the influence of every feature per predicted value. There-fore, the feature influence can be determined by using the aggregated influence of every feature in the prediction model on predicted values. The method is proposed by Lundberg et al. (2018), and it uses game theory as its basis to calculate SHAP values. SHAP values characterize the ef-fect of the independent variable when that independent variable is eliminated from the model.
According to the author, the model can be used for explaining machine learning algorithms which were considered as a black box, it also outperforms other algorithms that are used for explaining complex models. The detailed explanation and interpretation of SHAP values can
3.3 Results be found in Appendix F and SHAP summary plots for each topic and learning behavior can be found in Appendix G. As the number of models analyzed is related to the number of topics and overall sustainability score, there are 5 different analyses for interpreting important supplier characteristics for each topic. Detailed tables of the results can be found in Appendix H. The tables are constructed by analyzing the SHAP values for the relevant independent variable for the relevant model. Columns represent the independent variables; rows represent the learn-ing behaviors. The effects of independent variables on learnlearn-ing behaviors for a specific topic reported for each variable group. It should be noted that the interpreted results are the ones which are discussed and confirmed by experts at Philips. In Table 13, the relationship between activities performed by suppliers and its effects on learning behaviors can be found.
• Suppliers who perform sub-assembly activity are expected to be fast learner suppliers in health and safety topic. As the activity can be considered as a less risky activity, it might be easier for them to improve the issues that may arise.
• Suppliers who perform logistics and distribution activity are expected to be fast learner suppliers. Interviews with experts revealed that logistics and distribution suppliers are expected to care more about sustainability as there are already sustainability develop-ments in the industry such as ’green logistics’ and ’inverse logistics’. Therefore, they are expected to improve more and faster than other suppliers in SSP program. Those suppli-ers are expected to learn fast in environment, health and safety and human capital topic.
It makes sense as logistics and distribution activity is closely related to those topics.
• Suppliers who perform metal stamping activity are more likely to be indifferent in health and safety topic. The conclusion results from that the nature of metal stamping activ-ity is considered as risky. Consequently, those suppliers may take more time to solve health and safety issues. That is why they cannot show significant improvement amounts throughout the sequences.
• Suppliers who perform final assembly are expected to be fast learner suppliers in envi-ronment and business ethics topics. According to expert opinion, it can be because of final-assembly and sub-assembly is closely related and less risky activities. Therefore, applying improvement actions in terms of environment and business ethics topics can be easier and less time consuming for them. That is why they can improve faster than other suppliers that are not performing final assembly.
• Suppliers who perform clean room activity are considered as slow learners in health and safety and human capital topics. Interviews with experts revealed that suppliers that are performing clean room activity are considered as high mature suppliers. Therefore, the room for improvement might be less for them. That is why they are expected to be slow learner suppliers as there is not much improvement potential for those suppliers.
However, the relationship between performing clean room activity with business ethics topics could not be explained by experts.
3.3Results Table 13: Activities that affect learning behavior of suppliers in each topic
Class Subassembly Logistics and
Distribution
Metal Stamping Final Assembly Clean Room Plastic Molding
Lagged Fast Learner
Health & Safety (-) Business Ethics (-) Business Ethics (+)
Fast Learner Health & Safety (+) Environment (+) Business Ethics(+)
Health & Safety (+) Environment (+) Human Capital (-) Human Capital(+)
Slow Learner Human Capital (-) Environment(-) Health & Safety(+)
Human Capital (+)
Indifferent Environment (-) Health & Safety(+) Business Ethics(-)
(+) represents the positive relationship between activities and class whereas (-) represents the negative relationship.
Table 14: Facilities that affect learning behavior of suppliers in each topic
Class Dormitory Chemical
Warehouse
Kitchen Hospital
Lagged Fast Learner
Environment (+) Environment (+)
Health & Safety (+) Fast Learner Environment (-)
Health & Safety (-) Human Capital (-)
Slow Learner Health & Safety (+) Business Ethics (-) Environment (-) Human Capital(+)
Indifferent Business Ethics(+) Health & Safety (-) Environment(+) (+) represents the positive relationship between activities and class whereas (-) represents the negative relationship.
30
3.3 Results
• Suppliers that are performing plastic molding activity are less likely to be indifferent sup-pliers in business ethics topic. As the activity can be considered as more troublesome than other activities, the suppliers are closely monitored by regulations about issues related to business ethics according to experts. That is why they have to show improvement in order not to have problems with regulations. Therefore, those suppliers are not expected to be indifferent suppliers.
When the effects of the facilities of suppliers on learning behaviors interpreted, Table 14 is examined as,
• Suppliers who have dormitory on their site are less likely to be fast learner suppliers on environment, human capital and health and safety topics. According to experts, having a dormitory can be a sign of having more people in the workforce and its labor-intensive.
That is why it results in additional issues in terms of environment, health and safety and human capital topics. As a consequence, those suppliers evolve less than other suppliers that do not have dormitories in their sites.
• Suppliers who have a chemical warehouse on their site are more likely to be indifferent suppliers on business ethics topic. It can result from that managing a chemical ware-house may not be easy in terms of business ethics. Therefore, it may take more time to improve issues that arise from having a chemical warehouse. Consequently, those sup-pliers cannot obtain significant improvement amounts during the process.
• Suppliers who have a kitchen in their sites are expected to be lagged fast learners on en-vironment and health and safety topics. The reason might be that having a kitchen might result in several environmental and health and safety issues that can be solved easily.
However, a delay can be expected to see the effects and implementation of solutions.
That is why they are classified as lagged fast learner suppliers if they have a kitchen in their sites.
• Another facility that has a relationship with environment topic is having a hospital in the suppliers’ site. According to experts, having a hospital in their sites can be seen as a sign of high maturity. Therefore, those suppliers have less room for improvement and their evolution of sustainability score can be less than other suppliers because of that reason.
3.3 Results Table 15: General Information that affect learning behavior of suppliers in each topic
Class Total Number of
Fast Learner Environment(+) Human Capital (+) Health & Safety (-) Slow Learner Health & Safety (+) Environment (-)
Human Capital(+)
Indifferent Human Capital (-)
(+) represents the positive relationship between activities and class whereas (-) represents the negative relationship.
Furthermore, general information related to suppliers is examined. It can be seen from Table 15 that suppliers with a high number of workers are expected to be slow learner suppliers. It can be interpreted as more workers imply more health and safety improvement issues. There-fore, those suppliers may improve less than other suppliers as they have more points to focus and their resources may not be enough to handle all the issues. Suppliers with a high percent-age of manpercent-agement and staff employees are expected to be fast learner suppliers. The reason might be that the management and staff employees play a vital role in executing and imple-menting the actions. Higher management and staff employees also mean a higher level of a corporate structure. Therefore, those suppliers improve faster than other suppliers. Another feature that affects the learning behaviors is whether a supplier is a part of MNO or not. Ac-cording to experts, being a part of MNO brings suppliers more training and education to their workforce. Therefore, those suppliers are expected to learn faster in human capital topic. In addition to that, suppliers that are located in Jiangsu province in China increases the likelihood of being a fast learner supplier in health and safety topic. During the interviews with experts at Philips, the reason can be explained as that governmental regulations and controls are stricter in Jiangsu province compared to other provinces. That is why suppliers that are located in Jiangsu province are expected to learn faster.
Other than activities, facilities and general information variables, having specific certificates also affects the learning behavior significantly in some of the topics. The certificates that sup-pliers may have are ISO 14001, ISO 9001, OHSAS 18001, SA 8000 and other certificates. These certificates are related to environment, general quality requirements, health and safety and hu-man capital topics respectively. The effects of certificates on learning behavior can be explained as follows:
• Suppliers that have ISO 14001 document are expected to be fast learner suppliers in en-vironment and human capital topics. According to experts, it is expected as the certi-fications, especially ISO 14001, are considered as evidences that suppliers show effort towards improving their processes.
• Suppliers that have OHSAS 18001 document are expected to be indifferent suppliers in business ethics topic. The reason might be that suppliers that have the document can be considered as high maturity suppliers. As a consequence, instead of increasing their
3.3 Results sustainability score, they aim to keep their current scores.
• Suppliers that have other certificates are more likely to be slow learner suppliers. It can result from those suppliers already have high maturity levels. Therefore, they cannot learn fast as they do not have enough room for improvement.
Other variables have also influence on learning behavior on different topics. However, accord-ing to interviews with experts, the effects of those variables cannot be explained. Therefore, those variables are shown in Appendix H but their effects cannot be interpreted.
3.3.1 Validation Score (Overall Sustainability Score)
As the score of each topic can be aggregated into a score which is called overall sustainability score or validation score, the effects of features on learning behavior of overall sustainability score can be investigated as well. Table 16 represents the effects of supplier characteristics on learning behavior.
Table 16: Effects of independent variables on overall score
For validation score,
• Suppliers that perform final assembly, sub-assembly and logistics and distribution activ-ity are expected to be fast learner suppliers. The reason results from the nature of ac-tivities. As final assembly and sub-assembly activities are less risky activities, suppliers evolve more than others easily about the sustainability issues. For logistics and distri-bution activity, they are related to sustainability issues according to experts. Therefore, they are considered as fast learner suppliers. Suppliers that perform clean room activity are expected to be slow learner suppliers. Interviews revealed that suppliers with clean room activities are considered as high mature suppliers. Consequently, they have less room for improvement. That is why they are categorized as slow learners.
3.3 Results
• Suppliers with more workers and a higher percentage of management and staff employ-ees are expected to be lagged fast learner suppliers. The result can be interpreted as the high number of workers means more people to deal with in case of a sustainability is-sue. Therefore, these suppliers may not improve in the first sequences (especially from sequence 1 to sequence 2) but later they catch up with the momentum and learn faster.
In addition to that, a higher percentage of management and staff means more people to be convinced for proper implementation of improvement actions. After some delay, the management and staff employees start to adapt the change and increases the time that requires for implementation of actions.
• Suppliers that have a waste water treatment facility in their sites are expected to be fast learner suppliers. According to experts, having a waste water treatment facility implies that suppliers care about sustainability at all. Therefore, those suppliers learn faster.
• Being a part of MNO increases the likelihood of being lagged fast learner suppliers. The reason might be that as there are additional stakeholders and decision-makers in MNO suppliers, there needs to be some time to convince those stakeholders and decision-makers to implement the suggested actions.
• Suppliers that are located in Jiangsu province are less likely to be slow learner suppliers.
As the experts say that the regulation and governmental control are stricter in Jiangsu province, those suppliers are expected to improve throughout the sequences.
As an addition to those interpretations, there are interaction effects between supplier charac-teristics that influence the learning behavior. Table 17 can be examined to see the important interaction effects for the overall sustainability score.
Table 17: Interaction effect between independent variables for validation score
Class Interaction Effect
Lagged Fast Learner Final Assembly with Initial Score
MNO with Percentage of management and staff
Slow Learner Subassembly with Initial Score
• A higher initial score increases the effect size of final assembly activity if a supplier per-forms final assembly for being lagged fast learner suppliers. The reason can be suppliers with a higher sustainability score needs additional time to adapt SSP for implementing the suggested actions properly. Therefore, they are classified as lagged fast learners.
• A higher percent management and staff employees decreases the effect size of MNO for being lagged fast learner if a supplier is a part of MNO. It can be interpreted as a higher percentage of management and staff employees implies a hierarchy. As a result, the people that are in charge must support the SSP in terms of implementing the actions.
That is why they are considered as lagged fast learner suppliers.