• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Tools with Artificial Intelligence >Uplift Modeling for Cost Effective Coupon Marketing in C-to-C E-Commerce
【24h】

Uplift Modeling for Cost Effective Coupon Marketing in C-to-C E-Commerce

机译：C-to-C电子商务中具有成本效益的优惠券营销的提升模型

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

E-commerce companies often provide marketing incentives such as price discount coupons to motivate new customers to make their first purchase. However, many customers make purchases only when coupons are distributed to them; they stop making purchases after using the coupons. Thus, for cost-effective marketing, it is desirable for companies to distribute marketing coupons to new customers that have the highest potential to make future purchases without continued coupon incentives. However, it is difficult for e-commerce companies to identify the new customers to be targeted within 30 hours of registration. In this study, we address this problem using uplift modeling for cost-effective marketing. Uplift modeling can be used to identify the time when there is a causal relationship between coupon distribution and future non-coupon purchases. The ability to identify these causal relationships can allow a company to distribute coupons to the most promising customers and improve its business. Several studies have explained the benefits of uplift modeling in real-world e-commerce businesses. In this study, we demonstrate the results of uplift modeling for coupon distribution in a real-world Customer-to-Customer (C-to-C) e-commerce platform. We show that uplift modeling decreases marketing costs by 39.0% with only a negligible reduction in the number of acquired customers who make non-coupon purchases. However, it is difficult for E-commerce companies to identify the new customers to be targeted within 30 hours of registration. In this study, we address this problem using uplift modeling for cost-effective marketing. Uplift modeling can be used to identify the time when there is a causal relationship between coupon distribution and future non-coupon purchases. The ability to identify these causal relationships can allow a company to distribute coupons to the most promising customers and improve its business. Several studies have explained the benefits of uplift modeling in real-world E-commerce businesses. In this study, we demonstrate the results of uplift modeling for coupon distribution in a real-world Customer-to-Customer (C-to-C) E-commerce platform. We show that uplift modeling decreases marketing costs by 38.6% with only a negligible reduction in the number of acquired customers who make non-coupon purchases.
机译：电子商务公司通常会提供诸如价格折扣优惠券之类的营销激励措施，以激励新客户进行首次购买。但是，许多客户仅在将优惠券分发给他们时才进行购买。他们在使用优惠券后停止购买。因此，对于具有成本效益的营销，希望公司在没有持续的优惠券激励的情况下将营销优惠券分发给具有最大潜力进行未来购买的新客户。但是，对于电子商务公司来说，很难在注册后的30个小时内确定新的目标客户。在本研究中，我们使用提升模型来解决此问题，以实现具有成本效益的营销。提升模型可用于识别优惠券分配与将来的非优惠券购买之间存在因果关系的时间。识别这些因果关系的能力可以使公司向最有希望的客户分发优惠券并改善其业务。多项研究已经解释了提升模型在现实世界中的电子商务业务中的好处。在这项研究中，我们演示了在真实的客户对客户（C-to-C）电子商务平台中用于优惠券分配的提升模型的结果。我们显示，提升模型可将营销成本降低39.0％，而进行非优惠券购买的获得客户的数量仅微不足道。但是，对于电子商务公司来说，很难在注册后的30小时内确定新的目标客户。在本研究中，我们使用提升模型来解决此问题，以实现具有成本效益的营销。提升模型可用于识别优惠券分配与将来的非优惠券购买之间存在因果关系的时间。识别这些因果关系的能力可以使公司向最有希望的客户分发优惠券并改善其业务。多项研究已经解释了提升模型在现实世界中的电子商务业务中的好处。在这项研究中，我们演示了在真实的客户对客户（C-to-C）电子商务平台中用于优惠券分配的提升模型的结果。我们显示，提升模型可将营销成本降低38.6％，而进行非优惠券购买的获得客户的数量仅微不足道。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号