The online advertising management platform has become increasingly popular among e-commerce vendors/advertisers, offering a streamlined approach to reach target customers. Despite its advantages, configuring advertising strategies correctly remains a challenge for online vendors, particularly those with limited resources. Ineffective strategies often result in a surge of unproductive ``just looking'' clicks, leading to disproportionately high advertising expenses comparing to the growth of sales. In this paper, we present a novel profit-maximing strategy for targeting options of online advertising. The proposed model aims to find the optimal set of features to maximize the probability of converting targeted audiences into actual buyers. We address the optimization challenge by reformulating it as a multiple-choice knapsack problem (MCKP). We conduct an empirical study featuring real-world data from Tmall to show that our proposed method can effectively optimize the advertising strategy with budgetary constraints.

翻译：在线广告管理平台日益受到电商卖家/广告主的青睐，为精准触达目标客户提供了便捷途径。然而，尽管优势显著，如何正确配置广告策略仍然是线上卖家（尤其是资源有限者）面临的挑战。低效策略往往导致大量无效的“随便看看”点击激增，使得广告费用相比销售额增长呈现不合理的偏高。本文提出了一种面向在线广告定向选项的新型利润最大化策略。该模型旨在寻找最优特征组合，以最大化目标受众向实际购买者转化的概率。我们通过将优化问题重构为多选择背包问题来解决这一挑战。基于天猫真实数据的实证研究表明，所提出的方法能够在预算约束下有效优化广告策略。