Machine learning-based e-commerce platform repurchase customer prediction model

Liu, Cheng-Ju; Huang, Tienshou; Ho, Ping-Tsan; Huang, Jui-Chan; Hsieh, Ching-Tang

doi:10.1371/journal.pone.0243105

Cited by 27 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This segment is important as the company invest in new customers which uses the COCA model, cost of customer acquisition, and their lifetime value., then the customer is judged to be profitable as the customer becomes promotor through word of mouth as well as distributor being existing and repeat customer. [15] International Journal of Intelligent Communication, Computing and Networks Open Access Journal (ISSN: 2582-7707) https://doi.org/10.51735/ijiccn/001/20 65…”

Section: Customer Lifetime Valuementioning

confidence: 99%

Performance Analysis and Optimization of Customer E-Commerce using Data Segmentation Algorithm

2021

IJICCN

View full text Add to dashboard Cite

The online retail industry is the world's largest growing sector having a vast amount of online sales data to promote and sell their products. However, overloaded data emerge on the customers' side. Customers today expect personalized, relevant information and offers based on their preferences, recent interactions, and the latest product and support experiences. They are ready to take off their journeys with a single poor experience.Companies cannot risk faltering or even provide a below an average interaction at any step along the entire customer journey to affect their revenue. Effective segmentation will help to identify identical and differentiated customers, as proper segmentation will be developed insights inform to the strategic road map which intends to take benefit of profit-driving opportunities with each segment of customers. This could shorten the customer purchase cycle, building customer loyalty, driving higher spend, lowering service, or deepening cross-product and up-selling penetration and support costs. Customer segmentation will target potential customers, by analyzing cross-selling and up-selling product bundling techniques, preferring geographic segmentation, predicting customer lifetime value, and considering historic values for future prediction. The paper discusses four classification algorithms that are comparatively tested to find the best fit classifier to build a personalized recommendation system, giving the customer their personalized products. The study proposes data segmentation modeling and optimizes classification algorithms for driving continuous e-commerce growth. Optimizing the gained segmented values for classification to make the model more precise and accurately segment customers for achieving more effective customer marketing through personalization, to enhance sales by boosting potential customers.

show abstract

Section: Customer Lifetime Valuementioning

confidence: 99%

Performance Analysis and Optimization of Customer E-Commerce using Data Segmentation Algorithm

2021

IJICCN

View full text Add to dashboard Cite

show abstract

“…True positives (TP), false positives (FP), true negatives (TN), and false negatives (FN) are the four cells of the matrix in this context (FN). The following presents a description of each parameter [4]. The prediction accuracy is defined as the number of correct predictions divided by the total number of input samples.…”

Section: Prediction Modelsmentioning

confidence: 99%

“…One possible way of exploiting the data of customers' purchasing decisions is via machine learning techniques to construct accurate prediction models. Machine learning is a highly advanced, rapid, and accurate technology [4]. In the customer relationship management domain, the use of machine learning techniques for predictive purposes on a customer base is frequently investigated, with customer churn prediction being the most prominent goal.…”

Section: Introductionmentioning

confidence: 99%

Predicting Consumer Purchasing Decisions in the Online Food Delivery Industry

Madani¹,

Alshraideh²

2021

Advances in Machine Learning

View full text Add to dashboard Cite

This transformation of food delivery businesses to online platforms has gained high attention in recent years. This due to the availability of customizing ordering experiences, easy payment methods, fast delivery, and others. The competition between online food delivery providers has intensified to attain a wider range of customers. Hence, they should have a better understanding of their customers’ needs and predict their purchasing decisions. Machine learning has a significant impact on companies’ bottom line. They are used to construct models and strategies in industries that rely on big data and need a system to evaluate it fast and effectively. Predictive modeling is a type of machine learning that uses various regression algorithms, analytics, and statistics to estimate the probability of an occurrence. The incorporation of predictive models helpsonline food delivery providers to understand their customers. In this study, a dataset collected from 388 consumers in Bangalore, India was provided to predict their purchasing decisions. Four prediction models are considered: CART and C4.5 decision trees, random forest, and rule-based classifiers, and their accuracies in prodividing the correct class label are evaluated. The findings show that all models perform similarly, but the C4.5 outperforms them all with an accuracy of 91.67%.

show abstract

“…Most of the studies focus on the discussion of purchase intention [ 9 – 11 ] and influencing factors [ 12 – 15 ]. Later, the methods of mathematical statistics were introduced to simplify the behavior prediction into a two-category problem [ 16 , 17 ]. KNN is one of the simplest classification methods, which is widely used in vehicle sales forecast [ 18 ], health monitoring [ 19 ], housing price forecast [ 20 ], and other fields.…”

Section: Introductionmentioning

confidence: 99%

An improved deep forest model for prediction of e-commerce consumers’ repurchase behavior

Zhang

Wang

2021

PLoS ONE

View full text Add to dashboard Cite

As the Internet retail industry continues to rise, more and more consumers choose to shop online, especially Chinese consumers. Using consumer behavior data left on the Internet to predict repurchase behavior is of great significance for companies to achieve precision marketing. This paper proposes an improved deep forest model, and the interactive behavior characteristics of users and goods are added into the original feature model to predict the repurchase behavior of e-commerce consumers. Based on the Alibaba mobile e-commerce platform data set, first construct a feature engineering that includes user characteristics, product characteristics, and interactive behavior characteristics. And then use our proposed model to make predictions. Experiments show that the model’s overall performance with increased interactive behavior features is better and has higher accuracy. Compared with the existing prediction models, the improved deep forest model has certain advantages, which not only improves the prediction accuracy but also reduces the cost of training time.

show abstract

Machine learning-based e-commerce platform repurchase customer prediction model

Cited by 27 publications

References 11 publications

Performance Analysis and Optimization of Customer E-Commerce using Data Segmentation Algorithm

Performance Analysis and Optimization of Customer E-Commerce using Data Segmentation Algorithm

Predicting Consumer Purchasing Decisions in the Online Food Delivery Industry

An improved deep forest model for prediction of e-commerce consumers’ repurchase behavior

Contact Info

Product

Resources

About