User Guide
Why can I only view 3 results?
You can also view all results when you are connected from the network of member institutions only. For non-member institutions, we are opening a 1-month free trial version if institution officials apply.
So many results that aren't mine?
References in many bibliographies are sometimes referred to as "Surname, I", so the citations of academics whose Surname and initials are the same may occasionally interfere. This problem is often the case with citation indexes all over the world.
How can I see only citations to my article?
After searching the name of your article, you can see the references to the article you selected as soon as you click on the details section.
  Citation Number 3
 Views 11
 Downloands 4
Yapay Sinir Ağını Kullanarak Müşteri Memnuniyeti Analizi
2020
Journal:  
Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi
Author:  
Abstract:

Günümüz teknolojilerinde en önemli merak konularından biri ileriyi tahmin etmek olmuştur. Bu konuda birçok çalışma makine öğrenmesi üzerine yoğunlaşmıştır ama doğrusal olmayan durumlarda klasik makine öğrenmesi yöntemleri yeterli gelmemiştir. Yapay sinir ağları da eldeki verilerden yola çıkarak tahminler yapabilmemize olanak sağlayan bir sistem olarak hayatımıza girmiştir. Müşteriye yönelik çalışan tüm kuruluşların daha fazla müşteri kazanabilmek ve var olan müşterilerini ellerinde tutabilmek için müşterilerinin memnuniyetlerini öğrenmeleri gerekmektedir. Bu memnuniyet durumu içine sadece nesnel veriler değil insan duyguları da girebileceği için doğrusal bir denklem oluşturulamamaktadır. Eldeki veriler iyi analiz edilerek, yeni gelecek müşteriler için de doğru kararlar verilip onların kalıcılığının arttırılması gerekmektedir. Klasik makine öğrenmesi bu tür bir uygulamada yetersiz kalmaktadır, ancak otomatik olarak eğitilen ve doğrusal olmayan bileşenler içeren yapay sinir ağları doğruluğu yüksek sonuçlar verebilmektedir. Yapay sinir ağları sayesinde doğrusal olmayan denklemler kurularak bu uygulamalara yönelik tahminlerin en iyi şekilde yapılması amaçlanmaktadır. Son yıllarda yapılan karşılaştırmalar ve çalışmalar da yapay sinir ağlarının klasik makine öğrenmesi yöntemlerine göre doğrusal olmayan durumlarda daha iyi sonuç verdiğini göstermektedir. Bu çalışma da derin öğrenme ile müşteriler üzerinde memnuniyet analizi ve tahmini yapılırsa daha iyi sonuçlar alınabileceğini ortaya koymaktadır. Bu makalede bir yapay sinir ağında bu uygulama özelinde karşılaşılan durumlar raporlanmaktadır. Çalışmamız müşteri memnuniyet analizi için ağdaki parametrelerin nasıl ayarlanması gerektiğini belirtmekte ve farklı algoritma seçimlerinin nasıl sonuç verdiğini göstermektedir. 

Keywords:

Customer satisfaction analysis using artificial nerve network
2020
Author:  
Abstract:

One of the most important issues in today’s technology is to predict the future. Many studies have focused on machine learning, but in nonlinear situations, the classic machine learning methods have not been sufficient. Artificial nerve networks have also entered our lives as a system that allows us to make predictions from the data available. All organizations that work towards customers need to learn their customer satisfaction to gain more customers and keep their existing customers in their hands. A linear equation cannot be created in this state of satisfaction because it can enter not only objective data, but also human emotions. The data available is well analyzed, the right decisions are made for new future customers and their durability is increased. Classical machine learning remains insufficient in this type of application, but the accuracy of artificial nerve networks containing automatically trained and nonlinear components can give high results. Through the artificial nerve networks, it is intended to make the best forecasts for these applications by setting nonlinear equations. Comparisons and studies in recent years also show that artificial nerve networks have better results in nonlinear situations than the classic machine learning methods. This study also shows that if customer satisfaction analysis and estimates are done with deep learning, better results can be obtained. This article reports the situations encountered in this application in an artificial nerve network. Our study indicates how the parameters in the network should be adjusted for customer satisfaction analysis and shows how different algorithm choices result.

Keywords:

Customer Satisfaction Analysis Using Artificial Neural Network
2020
Author:  
Abstract:

One of the most important curiosity issues in today's technologies has been to predict the future. Many studies have focused on machine learning, but in nonlinear cases, classical machine learning methods are not enough. Artificial neural networks have entered our lives as a system that allows us to make predictions based on the available data. All organizations working for the customers need to learn the satisfaction of their customers in order to gain more customers and keep their existing customers. A linear equation cannot be created for this satisfaction, since not only objective data but also human emotions can be introduced. By analyzing the data well, it is necessary to make the right decisions for new future customers and increase their permanence. Classical machine learning is inadequate in this kind of practice, but automatically trained neural networks that include non-linear components can give results having high accuracies. Non-linear equations are established by means of artificial neural networks and it is aimed to make the best estimates. In recent years, comparisons and studies have shown that artificial neural networks give better results in nonlinear cases compared to classical machine learning methods. This study shows that better results can be obtained if satisfaction analysis are conducted on customers using deep learning methods. In this paper, situations encountered in this application which is using an artificial

Keywords:

Citation Owners
Attention!
To view citations of publications, you must access Sobiad from a Member University Network. You can contact the Library and Documentation Department for our institution to become a member of Sobiad.
Off-Campus Access
If you are affiliated with a Sobiad Subscriber organization, you can use Login Panel for external access. You can easily sign up and log in with your corporate e-mail address.
Similar Articles








Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi

Field :   Mühendislik

Journal Type :   Ulusal

Metrics
Article : 782
Cite : 1.924
2023 Impact : 0.157
Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi