Collaborative Research: Integrated Data-Driven Methodologies to Addressing the Driver Turnover and Shortage Problems in Truckload Transportation

在卡车运输行业，司机流动率高是一个长期问题，每年的成本高达28亿美元。一个主要原因是延长了司机的道路时间，这主要是工业中最常用的点对点调度的结果。另一个变得越来越重要的相关问题是司机短缺，由于婴儿潮一代的退休，经济的改善以及新实施的服务时间规定，估计十年内将达到239 K。该研究将全面调查司机流动和短缺问题，并通过面向系统的设计重点，包括新的积极主动的运营模式来解决这些问题。与现有的操作实践相比，系统方法框架将考虑所有利益相关者（司机，公司和客户）的观点，并通过描述性，预测性和规范性分析对当前和新系统及其操作进行建模和分析。这项研究的结果，预计将在解决营业额和短缺的问题，通过提供一个面向系统的框架，结合了运营和营业额相关的成本，同时提高驾驶员的满意度与数据驱动的协同调度工具产生重大影响。这项研究有可能大大降低该行业数十亿美元的非生产性成本，并通过以下方式造福社会：（1）支持司机工作（和家庭）的健康、繁荣和福利得到改善，2）为新的劳动力释放就业机会的潜力，以及3）通过改进的运输操作来降低成本。系统设计和操作可以通过更好地适应个人对位置的偏好来提高驾驶员满意度，时间表的规律性，里程和其他因素，同时也改善了经济措施，对所有利益相关者都很重要。系统开发将按照一种面向系统的办法进行，这种办法是围绕三个综合分析部分的框架进行的。这些组件将是1）描述性（设计和收集来自司机和调度员群体的现场数据，以确定影响卡车运输和周转的因素及其量化贡献），2）预测（将这些数据应用于在新的协作调度范例的背景下设计新的数据驱动的人员流动预测模型），以及3）规定性的（通过结合了协作调度/数据驱动的周转预测并考虑操作成本的优化和仿真框架来设计最佳中继和点对点网络（例如，空重定位）以及通过数据驱动的周转预测模型获得的周转成本）分析方法。

In the Truckload transportation industry, high driver turnover is a chronic problem, representing an annual cost of up to $2.8 billion. A primary reason is extended on-road times for drivers, largely a consequence of the point-to-point dispatching most often used in industry. Another related problem that is becoming increasingly important is the driver shortage, estimated to reach 239K in a decade, due to the retirement of the baby-boomer generation, an improving economy, and newly implemented hours-of-service regulations. The research will comprehensively investigate the driver turnover and shortage problems and address them through a systems-oriented design focus that also includes new proactive operational paradigms. In contrast to existing operational practices to fire-fight individual issues as they arise, a systems approach framework will take into account the perspectives of all stakeholders (drivers, companies, and customers) and involve modeling and analysis of both current and new systems and their operations via descriptive, predictive, and prescriptive analytics. The outcome of this research is expected to make substantial impact in addressing the turnover and shortage problems by providing a systems-oriented framework that incorporates both operational and turnover related costs while improving driver satisfaction with a data-driven collaborative dispatching tool. The research has the potential to significantly reduce an unproductive cost on the order of billions in the industry, and to benefit society by: 1) supporting the driver workforce (and families) with improved health, prosperity, and welfare, 2) unlocking the potential for employment opportunities for new workforce, and 3) reducing costs with improved transportation operations.The system design and operations can improve driver satisfaction by better accommodating individual preferences for location, schedule regularity, mileage, and other factors while also improving economic measures important to all stakeholders. System development will proceed following a systems-oriented approach that is structured around a framework of three integrated analytical components. These components will be the product of 1) descriptive (designing and collecting field data from groups of drivers and dispatchers to determine the factors affecting truckload operations and turnover as well as their quantified contributions), 2) predictive (applying these data to the design of a new data-driven turnover prediction model in the context of a new collaborative dispatching paradigm), and 3) prescriptive (designing optimum relay and point-to-point networks via an optimization-and-simulation framework that incorporates collaborative dispatching/data-driven turnover prediction and considers operational costs (e.g., empty repositioning) as well as turnover costs obtained by the data-driven turnover prediction model) analytical methods.