In the retail market, gathering marketing data is essential at different stages of advertisement and promotion; currently, this is achieved via online crowdsourcing. The jobs involving such tasks must be reasonably priced to attract part-time employees depending on the retail budget. Herein, a new approach is presented to enhance the task repricing performance of online crowdsourcing platforms using the density-based spatial clustering of applications with noise (DBSCAN) algorithm, genetic general regression neural network (G-GRNN), and AdaBoost meta-algorithm. Initially, DBSCAN is used to analyze the agent task distribution, task density, and ambient agent credibility. Then, G-GRNN and AdaBoost are applied to reprice the tasks and evaluate the completeness of the repricing. Results show that the proposed method can optimize the repricing outcomes and enhance the efficiency of the repricing process. This study was conducted to address the crowdsourcing pricing problem from the perspective of firms. The results demonstrate the effectiveness of the machine learning methods (DBSCAN, G-GRNN, and AdaBoost) in solving the task repricing problem.

在零售市场中，在广告和促销的不同阶段收集营销数据至关重要。目前，这是通过在线众包实现的。必须根据零售预算合理定价涉及此类任务的工作，以吸引兼职员工。在本文中，提出了一种新方法，该方法使用基于密度的应用程序空间聚类与噪声（DBSCAN）算法，遗传通用回归神经网络（G-GRNN）和AdaBoost元算法来提高在线众包平台的任务重定价性能。最初，DBSCAN用于分析座席任务分配，任务密度和环境座席信誉。然后，G-GRNN和AdaBoost用于对任务重新定价并评估重新定价的完整性。结果表明，该方法可以优化定价结果，提高定价效率。这项研究是从公司的角度解决众包定价问题的。结果证明了机器学习方法（DBSCAN，G-GRNN和AdaBoost）在解决任务重定价问题方面的有效性。