TY  - JOUR
TI  - A Comparison of Machine Learning Classifiers for Evaluation of Remarketing Audiences in E-Commerce
AB  - In this study, user data of an e-commerce site operatingin Turkey is examined. Users are those who have visitedthe site before, that is, they are in the remarketingaudience pool. The main goal is to make accuratepredictions for remarketing and thus offer customizedad packages for new visitors. Visitors are labeled as"Shoppers" and "Non-shoppers" based on their previousvisits. The data set is divided into two portions that donot intersect with each other as training and test sets.Three classification models based on artificial neuralnetworks, classification and regression trees (CART), andrandom forest are built to make predictions and thenclassification performances of these models arecompared.
AU  - Ekelik, Haydar
AU  - Emir, Şenol
DO  - 10.17153/oguiibf.879105
PY  - 2021
JO  - Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilimler Dergisi
VL  - 16
IS  - 2
SN  - 1306-6730
SP  - 341
EP  - 359
DB  - TRDizin
UR  - http://search/yayin/detay/439032
ER  -