A PCA-AdaBoost model for E-commerce customer churn prediction

Wu, Zengyuan; Jing, Lizheng; Wu, Bei; Jin, Lingmin

doi:10.1007/s10479-022-04526-5

Cited by 15 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional methods face challenges in predicting e-commerce customer churn because of the non-contractual nature of customers and high-dimensional, unbalanced data. The suggested PCA-AdaBoost model in [24] addresses these issues 1509 by introducing novel features into RFM analysis, minimizing data dimensions through principal component analysis, and employing adaptive boosting to manage unbalanced data. It improves performance metrics of churn prediction in ecommerce contexts and achieves an accuracy of 98%, precision of 98, recall of 99, and G-mean of 98%.…”

Section: -Literature Reviewmentioning

confidence: 99%

A Smart Model to enhance Customer retention in E-commerce

N. Abdelgawad,

M. Mostafa

2024

المجلة العلمية للبحوث والدراسات التجارية

View full text Add to dashboard Cite

Customer Relationship Management is essential for company's success, focusing on enhancing customer retention through early detection of churn. Due to the Exponential growth of data volume in e-commerce, it is essential to develop techniques to identify customer churn. Machine learning and CRM will effectively perform this task. Additionally predicting rush time linking optimized Employees distribution and minimizing technical issues to achieve customer retention. We applied K-means based on the RFM model and addressed imbalanced data using SMOTE-TOMEK. The Results revealed that XG-Boost outperformed other algorithms, including decision tree and random forest, achieving an accuracy of 87.37%, precision of 99.99%, recall of 74.68%, F1-score of 85.5%, and an AUC of 88%. Additionally, the analysis using zscore showed that rush times between 4:57 AM and 6:04 PM accounted for approximately 68% of all purchases.

show abstract

Section: -Literature Reviewmentioning

confidence: 99%

A Smart Model to enhance Customer retention in E-commerce

N. Abdelgawad,

M. Mostafa

2024

المجلة العلمية للبحوث والدراسات التجارية

View full text Add to dashboard Cite

show abstract

“…In the selected works from 2018-2023 focused on customer churn prediction, it was observed that the imbalance in churned and unchurned customers can bias machine and deep learning models, thus hindering generalization and increasing misclassification errors [164]. To address this, techniques such as re-sampling, class weighting, data augmentation, and ensemble methods can be used to mitigate the effect of imbalanced class data [165][166][167]. Additionally, the accuracy of ML and DL methods for churn prediction can be influenced by the presence of multiple types of data, such as numerical data on orders, textual after-purchase reviews, and socio-geo-demographic data [168].…”

Section: Customer Churn Predictionmentioning

confidence: 99%

A Brief Survey of Machine Learning and Deep Learning Techniques for E-Commerce Research

Zhang,

Guo,

Chen

et al. 2023

JTAER

View full text Add to dashboard Cite

The rapid growth of e-commerce has significantly increased the demand for advanced techniques to address specific tasks in the e-commerce field. In this paper, we present a brief survey of machine learning and deep learning techniques in the context of e-commerce, focusing on the years 2018–2023 in a Google Scholar search, with the aim of identifying state-of-the-art approaches, main topics, and potential challenges in the field. We first introduce the applied machine learning and deep learning techniques, spanning from support vector machines, decision trees, and random forests to conventional neural networks, recurrent neural networks, generative adversarial networks, and beyond. Next, we summarize the main topics, including sentiment analysis, recommendation systems, fake review detection, fraud detection, customer churn prediction, customer purchase behavior prediction, prediction of sales, product classification, and image recognition. Finally, we discuss the main challenges and trends, which are related to imbalanced data, over-fitting and generalization, multi-modal learning, interpretability, personalization, chatbots, and virtual assistance. This survey offers a concise overview of the current state and future directions regarding the use of machine learning and deep learning techniques in the context of e-commerce. Further research and development will be necessary to address the evolving challenges and opportunities presented by the dynamic e-commerce landscape.

show abstract

“…Their results showed that SVM‐CHAID hybrid algorithm performed better than other hybrid algorithms. Wu et al (2022) developed a PCA‐AdaBoost model for customer churn prediction and reached a better prediction performance than logit, SVM, and AdaBoost techniques.…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting customer churn using grey wolf optimization‐based support vector machine with principal component analysis

Kurtcan

Özcan

2023

Journal of Forecasting

View full text Add to dashboard Cite

Customer churn is a challenging problem that can lead to a loss of organizational assets. Organizations need to predict customer churn successfully in order to get rid of potential damages and gain a competitive advantage. The aim of this study is to provide a churn prediction model by including feature selection and optimization in classification. The study performs principal component analysis (PCA) to select the best features, support vector machine (SVM) to predict customer churn, and grey wolf optimization (GWO) to optimize the parameters of SVM. In other words, this study proposes a novel hybrid model called PCA‐GWO‐SVM to enhance the prediction ability in customer churn. A comparison experiment is carried out, evaluating the proposed model with the other classification algorithms. Experimental results show that the proposed PCA‐GWO‐SVM hybrid model produces higher accuracy, recall, and F1‐score than other machine learning algorithms such as logit, k‐nearest neighbors, naive Bayes, decision tree, and SVM.

show abstract

A PCA-AdaBoost model for E-commerce customer churn prediction

Cited by 15 publications

References 35 publications

A Smart Model to enhance Customer retention in E-commerce

A Smart Model to enhance Customer retention in E-commerce

A Brief Survey of Machine Learning and Deep Learning Techniques for E-Commerce Research

Predicting customer churn using grey wolf optimization‐based support vector machine with principal component analysis

Contact Info

Product

Resources

About