No abstract

No abstract

In a vendor managed inventory (VMI) system, the effects of financial incentives on the entire supply chain (SC) and on the individual firms are investigated in this study. To this end, order management, order replenishment and inventory control activities of a two-echelon SC are examined via modeling using discrete event simulation. By determining the appropriate parameters for the incentives with scenario analysis, balanced profit distribution between buyers and a supplier in VMI is established. Simulation outputs of the traditional model, VMI only and VMI with incentives models are compared based on profits with paired comparisons. In VMI with incentives, both buyers, and the supplier experience higher benefits than the traditional system. This study provides a new method which eliminates the unbalanced benefit distribution due to VMI and offers almost equal benefits to the participating firms. With financial incentives, firms are encouraged to share information with each other to work in a coordinated SC.

In recent years, machine learning models based on big data have been introduced into marketing in order to transform customer data into meaningful insights and to make strategic decisions by making more accurate predictions. Although there is a large amount of literature on demand forecasting, there is a lack of research about how marketing strategies such as advertising and other promotional activities affect demand. Therefore, an accurate demand-forecasting model can make significant academic and practical contributions for business sustainability. The purpose of this article is to evaluate machine learning methods to provide accuracy in forecasting demand based on advertising expenses. The study focuses on a prediction mechanism based on several Machine Learning techniques-Support Vector Regression (SVR), Random Forest Regression (RFR) and Decision Tree Regressor (DTR) and deep learning techniques-Artificial Neural Network (ANN), Long Short Term Memory B Yigit Kazancoglu

No abstract

Çevrimiçi moda sektörü son yıllarda hızlı bir şekilde büyümektedir. Bu sektörde yer alan moda ürünü görselleri miktarı da sürekli artış göstermektedir. Ürünleri tanımlama ve sınıflandırma yeteneğine sahip bir sistem, görsellere otomatik etiket eklenmesini sağlayarak hızlı erişime olanak verdiği gibi çalışanların iş yükünü de hafifletebilir. Ayrıca moda sınıflandırma sistemi müşterilerin beğenisine dayalı ürünler sunmada kullanılabilir. Büyük miktarlardaki görseli işleyebilmek için ise yüksek performanslı algoritmalara ihtiyaç duyulmaktadır. Son yıllarda derin öğrenme uygulamalarından Evrişimsel Sinir Ağları (CNN) görüntü analizinde başarısı ile ön plana çıkmaktadır. Literatürde bir çok CNN mimarisi yer almakla birlikte, sınıflandırma doğruluğunu arttıracak yeni CNN mimarilerine olan ihtiyaç artan görsel verisi ile birlikte devam etmektedir. Bu çalışma, 10 sınıfa ayrılmış moda ürünü görselleri içeren Fashion-MNIST veri setini kullanarak farklı CNN mimarileri önermektedir. Önerilen mimarilerle amaç L2 ve Dropout düzenleyici yöntemlerin tahmin başarısına olan etkisini araştırmaktır. Bu sayede, verileri daha iyi sınıflandıran CNN modeli araştırılmıştır. Çalışmada önerilen mimariler; temel CNN, L2 düzenleyici ile CNN, Dropout düzenleyici ile CNN ve son olarak her iki düzenleyiciyi içeren CNN modelleridir. Her iki düzenleyici yöntem de ağ ezberlemeyi azaltmıştır. Elde edilen sonuçlara göre Dropout içeren CNN mimarisi %94.3 doğruluk (accuracy) değeri ile en iyi performansı sunan model olmuştur.

Turkey is not only prosperous with a unique natural heritage but the cultural heritage of history of mankind and civilization. In Turkey, there are hundreds of thousands of hectares of natural protected environments with boundaries. Loss of site characteristics and dissolution caused by boundary restriction and change of status are particularly vital problems facing the hundreds of thousands of hectares naturally protected environments conserved by laws in Turkey. In the country, natural protected area is divided into three categories; 1) Sensitive area to be strictly protected, 2) Qualified natural protection areas 3) Sustainable protection and controlled usage areas. This study examines the evaluation of the Sustainable Protection and Controlled Usage Environments in Çeşme (İzmir / Turkey) district to determine the protection strategy and accurate determination based on scientific data. Based on this strategy, in Çeşme, İzmir, Turkey, 17 polygons which were specified as Sustainable Protection and Controlled Usage Areas (SPCUA) by GIS method are reevaluated by 3 specialists who were asked to answer the questions using "yes", "no", or "partly" in the chart. "yes" is given 2 points, "no" is given 0 points and "partly" is given 1 point. The goal of this paper is to examine whether there is a substantial difference between the groups specified by GIS method Using dependent sample T-Test. The result of the analysis showed there is no significant difference between the GIS method and the evaluations of all the specialists.

No abstract