Browsing by Author "Kaya, Ecem"

Now showing 1 - 2 of 2

Makine Öğrenimi Algoritmalarına Dayalı Çevrimiçi Pazar Yeri Satış Tahmininin Analizi: Türk E-Ticaret Sitesi Örneği
(Abdullah Gül Üniversitesi / Sosyal Bilimler Enstitüsü, 2023) Kaya, Ecem; Sütçü, Muhammed; AGÜ, Sosyal Bilimler Enstitüsü, İşletme ve Ekonomi İçin Veri Bilimi Ana Bilim Dalı; 01. Abdullah Gül University
Internet shopping has grown in popularity as more of our daily requirements have begun to be addressed online. Learning about the preferences and motivations of customers in the Turkish market and guiding e-commerce platforms to adapt their marketing strategies and increase customer satisfaction is important for both resource allocation and cost minimization. The purpose of this paper is to estimate future sales for popular e-commerce sites based on behavioral factors such as discounts, price or free shipping. Therefore, real-time and experiment-independent data are collected from the sales made by one of Turkey's most popular e-commerce sites. In order to produce predictions, we employ Artificial Neural Networks, Support Vector Regression, K-Nearest Neighbors Regressor, OLS regression, and Nu-Support Vector Regressor. The models developed using machine learning algorithms attempt to estimate the number of sales based on independent factors such as price, discount rate, and user ratings. As the result of this research, we calculate and compare the accuracy of the models with root mean squared errors and R².
Movie Recommendation Systems Based on Collaborative Filtering: A Case Study on Netflix
(Erciyes Üniversitesi, 2021) Sütçü, Muhammed; Erdem, Oğuzkan; Kaya, Ecem; 0000-0002-4634-7638; 0000-0002-8547-7929; 0000-0002-8523-9103; AGÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü; Sütçü, Muhammed; Erdem, Oğuzkan; 01. Abdullah Gül University
User ratings on items like movies, songs, and shopping products are used_x000D_ by Recommendation Systems (RS) to predict user preferences for items that have_x000D_ not been rated. RS has been utilized to give suggestions to users in various domains_x000D_ and one of the applications of RS is movie recommendation. In this domain, three_x000D_ general algorithms are applied; Collaborative Filtering that provides prediction_x000D_ based on similarities among users, Content-Based Filtering that is fed from the_x000D_ relation between item-user pairs and Hybrid Filtering one which combines these_x000D_ two algorithms. In this paper, we discuss which methods are more efficient in movie_x000D_ recommendation in the framework of Collaborative Filtering. In our analysis, we use_x000D_ Netflix Prize dataset and compare well-known Collaborative Filtering methods_x000D_ which are Singular Value Decomposition, Singular Value Decomposition++, KNearest Neighbour and Co-Clustering. The error of each method is calculated by_x000D_ using Root Mean Square Error (RMSE). Finally, we conclude that K-Nearest_x000D_ Neighbour method is more successful in our dataset.