Prediction of Customer Purchase Satisfaction and Influencing Factors Investigation Based on Machine Learning

Tianyi Ouyang

2024

Abstract

In the field of e-commerce, shopping satisfaction is a key indicator for measuring consumers' overall perception of their shopping experience and is crucial for merchants to attract and retain customers. This study utilized the Amazon consumer behavior data from Kaggle and applied machine learning techniques to construct an efficient predictive model for accurately forecasting shopping satisfaction. The core of the research method involved the application of three classic machine learning algorithms: K-Nearest Neighbors (KNN), Decision Trees, and Random Forests. The specific research steps included data preprocessing, feature selection, dataset partitioning, and model prediction. In the data preprocessing phase, missing values in the dataset were removed. The feature selection phase employed the ExtraTreesClassifier algorithm for importance analysis, thereby determining the relative importance of each feature for model prediction. After feature selection, the study chose the most important features for the model and used cross-validation to evaluate the performance of the algorithms. Finally, after the model construction, this paper conducted hyperparameter tuning to optimize the model, resulting in the best predictive model, with the Decision Tree and Random Forest models showing excellent performance due to their high accuracy in classification tasks. The research results indicated that rating accuracy and personalized recommendation frequency are the two most important factors affecting shopping satisfaction. These findings provide guidance for online platforms to improve services and recommendation systems, which can help increase customer satisfaction and sales.

Paper Citation

in Harvard Style

Ouyang T. (2024). Prediction of Customer Purchase Satisfaction and Influencing Factors Investigation Based on Machine Learning. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 92-96. DOI: 10.5220/0013207100004568

in Bibtex Style

@conference{ecai24,
author={Tianyi Ouyang},
title={Prediction of Customer Purchase Satisfaction and Influencing Factors Investigation Based on Machine Learning},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={92-96},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013207100004568},
isbn={978-989-758-726-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Prediction of Customer Purchase Satisfaction and Influencing Factors Investigation Based on Machine Learning
SN - 978-989-758-726-9
AU - Ouyang T.
PY - 2024
SP - 92
EP - 96
DO - 10.5220/0013207100004568
PB - SciTePress