Predicting online shopping cart abandonment with machine learning approaches

Abstract

Excessive online shopping cart abandonment rates constitute a major challenge for e-commerce companies and can inhibit their success within their competitive environment. Simultaneously, the emergence of the Internet’s commercial usage results in steadily growing volumes of data about consumers’ online behavior. Thus, data-driven methods are needed to extract valuable knowledge from such big data to automatically identify online shopping cart abandoners. Hence, this contribution analyzes clickstream data of a leading German online retailer comprising 821,048 observations to predict such abandoners by proposing different machine learning approaches. Thereby, we provide methodological insights to gather a comprehensive understanding of the practicability of classification methods in the context of online shopping cart abandonment prediction: our findings indicate that gradient boosting with regularization outperforms the remaining models yielding an F1-Score of 0.8569 and an AUC value of 0.8182. Nevertheless, as gradient boosting tends to be computationally infeasible, a decision tree or boosted logistic regression may be suitable alternatives, balancing the trade-off between model complexity and prediction accuracy.

Investigation of Online Shopping Cart Abandonment on the Perspective of E- Procrastination Behavior

“…effective to be abandoned shopping cart. Overall, their findings showed that device used for online shopping can also affect purchasing behavior (Rausch et al, 2020).…”

Development of a hybrid model to plan segment based optimal promotion strategy

“…Recency (Meier, 2012), (Chen et al, 2012), (Mesforoush & Tarokh, 2013), (Danaee et al, 2013), (Tsai et al, 2013), (Zhang & Wang, 2014), (Sauro, 2015), (Hosseini & Mohammadzadeh, 2016), (Rezaeian et al, 2016), (Carnein & Trautmann, 2019), (Anitha & Patil, 2019) Frequency (Meier, 2012), (Chen et al, 2012), (Danaee et al, 2013), (Mesforoush & Tarokh, 2013), (Tsai et al, 2013), (Zhang & Wang, 2014), (Sauro, 2015), (Hosseini & Mohammadzadeh, 2016), (Rezaeian et al, 2016), (Aziz, 2017), (Dullaghan & Rozaki, 2017), (Anitha & Patil, 2019) Monetary (Meier, 2012), (Chen et al, 2012), (Tsai et al, 2013), (Mesforoush & Tarokh, 2013), (Danaee et al, 2013) (Hosseini & Mohammadzadeh, 2016), (Rezaeian et al, 2016), (Dullaghan & Rozaki, 2017), (Carnein & Trautmann, 2019), (Anitha & Patil, 2019) Demographic characteristics (Yadav et al, 2012), (Sauro, 2015), (Dullaghan & Rozaki, 2017), (Rausch et al, 2022) Page view (Meier, 2012), (Zhang & Wang, 2014),…”

“…In this work, in order to predict the segments of the customers, we use classification algorithms namely; Logistic Regression (LR), Support Vector Machines (SVM), Multi Layer Perceptron (MLP), Naive Bayes (NB), K-Nearest Neighbor (KNN) and Decision Tree (DT) algorithms. (Kotsiantis, Zaharakis, & Pintelas, 2007) makes a comprehensive review of the supervised classification algorithms and Hosseini & Mohammadzadeh, 2016; Xiao, Cao, Jiang, Gu, & Xie, 2017; Won, Kim, & Ahn, 2018; Qian, Tong, & Wang, 2019; Rausch, Derra, & Wolf, 2022) use these algorithms in CRM problems. Beside these base classifiers, we also utilize the well known ensemble methods, namely Adaboost (AB), Bagging (BG) and Random Forest (RF).…”

Estimating of Households Shopping on the Internet Using Random Forest Method

“…Yinelemeli Sinir Ağları tabanlı sınıflandırıcıların diğer yöntemlere göre daha başarılı olduğu görülmüştür. Rausch, Derra, & Wolf (2020) internetten alışveriş yapan bireylerden alışveriş sepetini terk edenleri makine öğrenmesi yöntemleri ile belirlemiştir. Gradient Boost (with regularization) yöntemi ile kurulan modelin en iyi doğruluk değeri elde ettiği görülmüştür.…”