基于机器学习的休闲零食电商营销策略优化

Optimization of E-Commerce Marketing Strategy for Leisure Snacks Based on Machine Learning

摘要: 随着电商平台成为休闲零食行业的核心销售渠道，挖掘消费者需求与优化营销策略成了解决行业供需衔接问题的关键部分。本文以休闲零食电商消费数据作为研究对象，通过整合多源数据创建研究体系：首先采用网络爬虫获取电商平台消费者的评论数据，再加上线上问卷数据补充消费偏好信息；其次通过与自编码器结合的随机森林算法识别消费者的首要关注因素，采用逻辑回归模型来量化变量对购买频率的影响；最后按照K-means聚类将消费者划分为四类群体，给出策略。研究结果可为休闲零食企业制定电商营销策略、提升市场竞争力提供数据支撑。

Abstract: With e-commerce platforms becoming the core sales channel for the leisure snacks industry, uncovering consumer demand and optimizing marketing strategies have become key to resolving supply-demand mismatches. This study takes e-commerce consumption data of leisure snacks as its research object and constructs a comprehensive research framework by integrating multiple data sources. Firstly, web crawler technology is used to obtain consumer review data from e-commerce platforms, and online questionnaire data is combined to supplement information on consumer preferences. Secondly, the random forest algorithm combined with an autoencoder is applied to identify the primary concerns of consumers, and the logistic regression model is used to quantify the impact of variables on purchase frequency. Finally, consumers are divided into four groups based on K-means clustering, and targeted strategies are proposed. The research results can provide data support for leisure snack enterprises to develop e-commerce marketing strategies and enhance market competitiveness.