Purpose-In this study, textile goods, of manufactured by a textile company, whether being returned because of defects or not has been investigated by data mining and machine learning techniques. Main purpose of the study is to determine which of the products passing through 15 different production lines during the manufacturing process being defective and faulty at the last stage. Methodology-In this study, there are 250 different variables and 72959 lines of data on the production line. In order to perform a data mining process, it is firstly necessary to understand the data and determine the process. For this, CRISP-DM algorithm has been used. Modelling and classification algorithms are applied to estimate the production of faulty goods. In the model, a supervised le arning model based machine learning methods have been used. The dimensions, loops and some statistical features of the data have been examined, and then it has been studied in the Python programming language. The feasibility of model and success rates have been evaluated with findings. Findings-The results of the model show that logistic regression and k-nearest neighbour algorithms give above %90 percentage confusion rate. It has been said that with this model is succesful for predicting defective and faulty product in manufacturing line. Conclusion-It has been tried to predict whether there will be faulty products that reduce quality. With this study, it has been aimed to give a signal to the production line in advance.

No abstract

Purpose-In this study, it is aimed to improve the production and quality control processes of a company operating in the textile industry. For this purpose, predicting faulty and refund products by using simulation of oversampling and undersampling applications. Methodology-In this study, there are 250 different variables and 72959 lines of data on the production line. These data have been taken from the last 1-year data of the firm. In this study, simulation has been done. New machine learning methods have been used by simulating. The reason for the simulation is that it was easy to detect the refund and faulty conditions made in a large lot group production in previous studies. However, the aim is to investigate whether the accuracy of the prediction algorithms will yield consistent results in terms of the increase in the number of refund and faulty products when production is made in a larger structure. In the simulation method, "oversampling" and "undersampling" methods have been used. While making simulation prediction, in the literature, boosting algorithms, which are used as ensemble machine learning techniques, have been used. In this study, simulation has been done as follows, while the number of production lots increased, refund and faulty products were increased within the same application. The reason for doing this is to investigate whether the prediction status in normal machine learning algorithms can be captured in a larger data stack. This process is called oversampling. Then, the "undersampling" method was applied. According to the "undersampling" method, it is aimed to determine the refund and defect situations in a smaller lot by taking samples of refund and defective products with less frequency. At the end of the study, the results were interpreted by applying boosting algorithms. Findings-As a result of the study, it is concluded that "undersampling" and "oversampling" simulations predict better than usual machine learning methodology. Conclusion-In this study, it has been observed that the ensemble machine learning algorithms (adaboost, xgboost, gradient boosting algorithms), which are one of the ensemble machine learning methods that emerged in 2016, were applied to the production data for the first time and showed success in the prediction of faulty and refund products.

In today's competitive market conditions, it is not enough to produce the high-quality product at the cheapest price. In addition, it is expected to deliver the product to the end user at any time and anywhere. The best way to achieve this is an effective logistics management. In recent years, it has been frequently talked about agility in creating an effective logistics management in the business world. In general, the word “agility” is a strategic response to the survival of businesses in today's competitive business environment. It should not be ignored that every business has a unique philosophy and produces / services under the influence of different environmental factors. For this reason, it can be said that there is no single agility concept being suitable for all businesses or every situation. On the other hand, agile logistics strategy can be achieved not only by minor changes, but also by completely differentiating the methods of performing activities. The creation of this differentiation depends on various success factors. In this context, the elements of success in agile logistics applications are as follows: “Managing Change and Uncertainty”, “Flexibility and Responsiveness in Service”, “Increasing the Value Shown to the Customer”, “Information Technologies”, “Flexible Human Resources” and “Building Collaborations Among Service Providers” specified. In this regard, it is obvious that the success factors in the agile logistics practices mentioned above are extremely important for the enterprises and increase the competitiveness of the enterprise. In the detailed literature review, the fact that no studies related to the prioritization of success elements in agile logistics applications have been encountered is a factor that increases the importance of the subject. In this study, the success factors of agile logistics practices in logistics firms in Giresun and Ordu provinces has been prioritized. Spherical fuzzy sets based AHP was used to prioritize these criteria.