This research supports improved salesforce outcomes for companies with independent sales representatives via the application of emerging technologies. It is framed in expectancy theory (in: Vroom, Work and motivation, Wiley, New York, 1964), Herzberg’s et al. (The motivation to work, Wiley, New York, 1959) two factor theory, and the job demands and resources model (JD-R) (Bakker and Demerouti in J Manag Psychol 22:309–328, 2007). The study analyzes the 2018 National Salesforce Survey (USA) commissioned by the Direct Selling Association (Washington, DC, USA). It identifies key factors in salesforce motivation and performance theories studied within these theoretical frames and channel-specific inputs for direct selling independent representatives. While researchers apply multiple methods to salesforce motivation and performance, the power of machine learning has not been applied to independent representatives and their unique circumstances. This research employs supervised learning algorithms for predictive analytics to create models for recruits and existing independent representatives. It finds that the most crucial factors align with expectancy theory for both. Allocated time for direct selling, ability to find new customers, gender, and adopting direct selling as a career play key roles in predicting sales success for individuals entering direct selling. The highest-performing representatives are characterized by time invested, experience of direct selling, recruitment, tenure, and use of technology. By predicting representative success factors, organizations can tailor recruitment, training, and incentives to maximize performance. Because independent sales representatives are not employees, understanding these factors is critical to firms engaging them. Translating established theory into testing with predictive analytics to identify meaningful success factors for rarely studied independent sales representatives has the potential to change the landscape for recruitment, retention, and success.

这项研究支持通过应用新兴技术来改善拥有独立销售代表的公司的销售人员成果。它以期望理论为框架（见：Vroom，工作与动机，Wiley，纽约，1964 年），Herzberg 等人。（工作动机，Wiley，纽约，1959）二因素理论，以及工作需求和资源模型（JD-R）（Bakker 和 Demerouti，J Manag Psychol 22：309-328，2007）。该研究分析了直销协会（美国华盛顿特区）委托进行的 2018 年全国 Salesforce 调查（美国）。它确定了在这些理论框架内研究的销售人员动机和绩效理论的关键因素以及直销独立代表的特定渠道输入。虽然研究人员应用多种方法来研究销售人员的动机和绩效，机器学习的力量尚未应用于独立代表及其独特情况。这项研究采用监督学习算法进行预测分析，为新员工和现有的独立代表创建模型。研究发现，最关键的因素与两者的预期理论一致。为直销分配的时间、寻找新客户的能力、性别以及将直销作为职业在预测进入直销的个人的销售成功方面发挥着关键作用。绩效最高的代表的特点是投入的时间、直销经验、招聘、任期和技术使用。通过预测代表性成功因素，组织可以定制招聘、培训和激励措施，以最大限度地提高绩效。由于独立销售代表不是员工，因此了解这些因素对于公司聘用他们至关重要。将既定理论转化为预测分析测试，为很少研究的独立销售代表确定有意义的成功因素，有可能改变招聘、保留和成功的格局。