Liang Jing, Zhou Xin, Yuan Chong, Chen Yong
School of Artificial Intelligence, Hubei Business College, Wuhan, 430079, China.
Wuhan Haiyun Health Technology Co., LTD, Wuhan, 430073, China.
Heliyon. 2024 Oct 17;10(23):e39482. doi: 10.1016/j.heliyon.2024.e39482. eCollection 2024 Dec 15.
In the retail industry, effective management of memberships is crucial, particularly within the pharmaceutical sector, as it fosters customer loyalty and drives sales growth. However, pharmacies often face challenges related to membership attrition and inactive members, which restrict the full potential of their membership programs. This research aims to address these challenges by optimizing pharmacy membership management systems through the utilization of big data technology. By leveraging the power of big data and employing machine learning algorithms, this study examines member data from multiple prominent pharmacy chains. The findings demonstrate the effectiveness of this approach in significantly increasing the level of activity among inactive memberships. Furthermore, this research unveils significant behavioral patterns among pharmacy members, shedding light on their preferences, purchasing habits, and interaction patterns. In this study, an artificial neural network (ANN) is employed to predict reactivation success rates, membership activity, and sales revenue based on website/app usage and member engagement. Two input factors, namely the frequency of website/app usage and member engagement score, are evaluated alongside three output factors: reactivation success rate, increase in membership activity levels, and increase in overall sales and revenue. Tailoring strategies based on member profiles and preferences enables pharmacies to re-engage customers and cultivate renewed loyalty. Importantly, these efforts yield positive impacts beyond membership activity, influencing overall sales and revenue generation for pharmacies. The ANN analysis reveals significant correlations and acceptable prediction errors. The insights gained from this study offer valuable information for enhancing membership management strategies and adjusting marketing efforts to cater to the specific needs and expectations of diverse customer segments. The practical, data-driven approach presented in this study equips pharmacies with the means to activate and re-engage dormant members. By harnessing the potential of big data technology and leveraging machine learning algorithms, pharmacies can optimize their membership management systems, enhance customer engagement, and improve their overall retail operations. This research underscores the significance of leveraging data-driven insights in the retail industry and showcases the transformative capabilities of big data technology in enhancing customer relationship management practices.
在零售业中，会员管理的有效性至关重要，尤其是在制药行业，因为它能促进客户忠诚度并推动销售增长。然而，药店常常面临与会员流失和不活跃会员相关的挑战，这限制了其会员计划的全部潜力。本研究旨在通过利用大数据技术优化药店会员管理系统来应对这些挑战。通过利用大数据的力量并运用机器学习算法，本研究考察了多个知名连锁药店的会员数据。研究结果表明这种方法在显著提高不活跃会员的活跃度方面是有效的。此外，本研究揭示了药店会员之间重要的行为模式，阐明了他们的偏好、购买习惯和互动模式。在本研究中，使用人工神经网络（ANN）根据网站/应用程序的使用情况和会员参与度来预测重新激活成功率、会员活跃度和销售收入。两个输入因素，即网站/应用程序的使用频率和会员参与度得分，与三个输出因素一起进行评估：重新激活成功率、会员活跃度水平的提高以及总销售额和收入的增加。根据会员档案和偏好制定策略使药店能够重新吸引客户并培养新的忠诚度。重要的是，这些努力产生的积极影响不仅限于会员活动，还会影响药店的整体销售和收入。人工神经网络分析揭示了显著的相关性和可接受的预测误差。本研究获得的见解为加强会员管理策略和调整营销努力以满足不同客户群体的特定需求和期望提供了有价值的信息。本研究提出的实用、数据驱动的方法为药店提供了激活和重新吸引休眠会员的手段。通过利用大数据技术的潜力并运用机器学习算法，药店可以优化其会员管理系统，增强客户参与度，并改善其整体零售运营。本研究强调了在零售业中利用数据驱动的见解的重要性，并展示了大数据技术在增强客户关系管理实践方面的变革能力。
