Customer behavior analysis based on purchasing history and reviews using automated decision-making systems

Recently, many shoppers have utilized online platforms, which can easily reveal consumer behavior and satisfaction with purchased products and the re-purchasing method. Problems Available: Some of the problems in the online purchasing app are the acceptance factor and the insufficient behavior of the consumer. The behavior is found in the online platform to analyze this problem. Solution: To overcome the problem, a consumer behavior analysis has to be performed to make people buy the product. Advanced Techniques Effectively Address Complex Issues: Machine learning and decision-making methods have been used to understand consumer behavior and decision-making. Machine Learning Techniques for Customer Behavior Analysis: Customer satisfaction can be identified for online purchasing using the machine learning method. This makes it easy to find online customer factorization. Techniques: Then, the decision-making process is used to analyze the customer’s data using the regression algorithm. Result: This results in the proposed model, the relationship of the many business models, the formation of the purchases that affect consumer needs, and the strategies that can be developed. Performance Result: The suggested system may be evaluated overall based on its capacity to raise sales, enhance customer happiness, and offer insightful data on consumer behavior. According to the provided tables, the proposed methods (KNN and ADMS) outperform the other algorithms (ID3, Decision Tree, and Logistic Regression) across a range of customer review counts in terms of accuracy (98.95%), precision (94.62%), recall (99.24%), and F1-score (96.87%) while processing customer reviews more quickly (0.063). Conclusions: In this study, the results enable the different platforms for analysis and decisions regarding shopping factors. This makes the direct collection of data, which can be analyzed.

Actions (login required)

View Item