Analysis of Different Predicting Model for Online Shoppers’ Purchase Intention from Empirical Data

Kabir, Rayhan; Ashraf, Faisal Bin; Ajwad, Rasif

doi:10.1109/iccit48885.2019.9038521

Cited by 20 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, RF is found as the most stable classifier that provides the most accurate customer purchase intention as well. Many works were investigated to determine customer intention using various methods [19,25,26] and some of them also found that RF is the best to identify customer purchasing rates as well [18,29]. However, they were not considered multiple feature engineering and data analytics methods to scrutinize it.…”

Section: Results Analysismentioning

confidence: 99%

“…It implemented real-time bidding algorithms for online advertising strategies, improving the effectiveness of advertisements and increasing last-touch attributions for campaign performance. Kabir et al [18] analyzed empirical data of online shoppers to predict their purchase intention. They found that RF was most suited to predict the customer's purchase intention where the highest accuracy of 90.34% was achieved by using gradient boosting with RF.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Online Customer Purchase Intention Behavior Applying Different Feature Engineering and Classification Techniques

Satu

Islam

2023

Preprint

View full text Add to dashboard Cite

Online shopping, known as e-shopping, has added a new dimension to the business sector. The concept of consumption among customers has changed significantly as a result of the quick growth of computer technology and e-commerce. The purpose of this work is to investigate the outcomes of different machine learning techniques and predict online shoppers’ purchasing intentions from e-commerce sites. In this study, we collected a dataset of online shoppers' purchasing intentions from the University of California Irvine (UCI) data repository. Different feature transformation techniques were employed in the primary dataset and generated transformed datasets. Besides, transformed datasets were balanced and detected outliers from them. Then, we applied different feature selection methods into primary and transformed balanced datasets and again generated several feature subsets. Further, different classifiers were implemented into all of these generated datasets and obtained different outcomes for them. In this work, Random Forest performed the best accuracy of 92.39% for Z-Score and Gain Ratio Attribute Evaluation transformed dataset. In addition, this classifier also provided the highest AUROC of 0.974 for Square Root and Gain Ratio Attribute Evaluation dataset. Therefore, Random Forest is a more stable classifier to predict customer purchase intention than other models.

show abstract

Section: Results Analysismentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Modeling Online Customer Purchase Intention Behavior Applying Different Feature Engineering and Classification Techniques

Satu

Islam

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…system also incorporated extreme boosting machines (ELM) and browsing content entropy features. It put into practice real-time bidding algorithms for online advertising tactics, enhancing last-touch attributions for campaign performance and boosting the efficacy of adverts.In their analysis of empirical data from online buyers, Kabir et al [22] found that gradient boosting with RF had the highest accuracy of 90.34% in predicting customers' purchase intentions. In his investigation on the many components of online shoppers' purchase intentions, Shi [24] found that while indicators like time spent and page values were favorably correlated with shopping intention, bounce rate and departure rate were adversely correlated.…”

Section: International Journal Of Innovative Research In Computer Sci...mentioning

confidence: 99%

E-Commerce Customer Behavior Using Machine Learning

Mall,

Pandey,

Tiwari

et al. 2024

International Journal of Innovative Research in Computer Science and Technology (IJIRCST)

View full text Add to dashboard Cite

The landscape of e-commerce has witnessed a transformative shift in consumer behavior, driven by the rise of digital technologies and online platforms. Understanding and predicting this dynamic behavior is crucial for businesses to thrive in the competitive online market. This review paper explores the application of machine learning (ML) techniques in analyzing and forecasting e-commerce customer behavior, with a specific focus on customer reviews. The advent of the internet has empowered consumers to express their opinions through online reviews, influencing purchasing decisions.ML models are increasingly employed to extract valuable insights from these reviews, offering businesses a nuanced understanding of customer preferences. The paper synthesizes existing literature on motivations behind online shopping, the role of trust and security, user experience, social influence, personalization, and post-purchase behavior. The literature review underscores the multifaceted nature of factors influencing e-commerce customer behavior and the pivotal role ML plays in decoding the complexities of consumer sentiments expressed in reviews. The conclusion highlights the need for continued research in ML approaches, especially in the context of big data, to enhance the accuracy of predictions and improve the overall understanding of e-commerce customer behavior.

show abstract

“…Random Forest Concept of Random Forest for producing a lot of correlated decision trees, where each decision tree acts as a collection of models. Every decision tree makes class predictions, with the maximum yield as the basis for the ultimate choice (Kabir, Ashraf, & Ajwad, 2019). The random forest classification method was developed using a decision tree technique that bases classification decisions on a random selection of attributes at each node.…”

Section: A Machine Learningmentioning

confidence: 99%

Comparison of Conventional Machine Learning and Deep Neural Network Algorithms in the Prediction of Monkey-Pox

Agustyaningrum,

Dahlia,

Pahlevi

2023

J. Ris. Inform.

View full text Add to dashboard Cite

Smallpox syndrome, or monkeypox, is an uncommon zoonotic viral infection brought on by the monkeypox virus, which belongs to the genus Orthopoxvirus and family Poxviridae. Injury-related mortality in primates ranges from 1 to 10%. Data mining is a method for analyzing data. Deep neural networks and traditional machine learning methods are used in data analysis. The Python programming language is used during the comparison procedure of this research algorithm to generate values for accuracy, f1 score, precision, recall, ROC, and AUC. The test results demonstrate that using sigmoid activation function parameters, the deep neural network algorithm's accuracy is 70.08%, F1 score is 79.18%, precision is 68.59%, recall is 62.65%, and AUC is 62.65%. Compared to conventional machine learning algorithms, the adagrad optimizer has a higher value with a learning rate of 0.01 and 0.2 dropouts. The conventional machine learning model algorithm has the best xgboost, F1 score, precision, recall, and AUC scores compared to other approaches: 64.40%, 64.45%, and 78.14%. According to these numbers, the average fairness disparity between deep neural network algorithms and traditional machine learning is 5.68%, F1 score is 13.79%, precision is 4.14%, recall is 1.75%, and AUC is 1.75%.

show abstract

Analysis of Different Predicting Model for Online Shoppers’ Purchase Intention from Empirical Data

Cited by 20 publications

References 12 publications

Modeling Online Customer Purchase Intention Behavior Applying Different Feature Engineering and Classification Techniques

Modeling Online Customer Purchase Intention Behavior Applying Different Feature Engineering and Classification Techniques

E-Commerce Customer Behavior Using Machine Learning

Comparison of Conventional Machine Learning and Deep Neural Network Algorithms in the Prediction of Monkey-Pox

Contact Info

Product

Resources

About