2020 年安徽省高校人文社科研究项目(SK2020A0090)
为了提升旅游电商服务水平 基于 K-means 聚类算法构建旅游电子商务平台 并采用随机梯度下降算法、自适应梯度优化算法和密度法对 K-means 聚类算法进行优化改进 结果表明:改进 K-means 聚类算法的系统响应速度相较于传统 K-means 聚类算法提升了 31.2% 电商平台推荐流量转化率为 2.93% 浏览行为中的推荐浏览率为 28.21% 购买行为中的推荐购买率为 15.37% 优于 Apriori 算法和 User-based CF 算法 利用改进 K-means 聚类算法构建旅游电子商务平台 能为平台用户提供个性化的旅游产品推荐 有效提升旅游产品的购买成交量 对旅游电商平台竞争力提升具有一定的实用价值
In order to improve the service level of tourism e-commerce a tourism e-commerce platform is constructedbased on K-means clustering algorithm and the K-means clustering algorithm is optimized by random gradient descent algorithm adaptive gradient optimization algorithm and density method. The experimental results show that the system response speed of the improved K-means clustering algorithm is 31.2% higher than that of the traditional K-means clustering algorithm the recommended traffic conversion rate of e-commerce platform is 2.93% the recommended browsing ratein browsing behavior is 28.21% and the recommended purchase rate in purchasing behavior is 15.37% which are betterthan the results by Apriori algorithm and user based CF algorithm.Using K-means clustering algorithm to build tourism ecommerce platform can provide personalized tourism product recommendation for platform users effectively improve thepurchase and trading volume of tourism products and has important practical value for improving the competitiveness oftourism e-commerce platform.
尹寿芳 ,张善智.K-Means 算法与数据挖掘在旅游电商平台设计中的应用[J].西昌学院学报(自然科学版),2022,36(1):92-96.