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

合作研究：综合数据驱动方法解决卡车运输中的司机流动和短缺问题

• 批准号: 1538115
• 负责人: Halit Uster
• 金额: $ 23.65万
• 依托单位: Southern Methodist University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-09-01 至 2020-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1538115&HistoricalAwards=false
• 关键词: Collaborative; Research; Integrated; Data; Driven

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.

在卡车运输行业，司机的高流动率是一个长期的问题，每年的成本高达28亿美元。一个主要原因是司机在路上的时间延长了，这在很大程度上是工业中最常用的点对点调度的结果。另一个日益重要的相关问题是司机短缺，由于婴儿潮一代的退休、经济改善以及新实施的服务时间规定，预计10年内将达到23.9万名司机。该研究将全面调查司机离职和短缺问题，并通过系统导向的设计重点解决这些问题，其中还包括新的主动操作范例。与现有的应对个别问题的操作实践相比，系统方法框架将考虑所有利益相关者（驱动程序、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。这项研究的结果有望通过提供一个以系统为导向的框架，结合运营和周转相关成本，同时通过数据驱动的协作调度工具提高司机满意度，对解决周转和短缺问题产生重大影响。这项研究有可能显著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)通过改善健康、繁荣和福利来支持司机劳动力（和家庭）；2)为新劳动力释放就业机会的潜力；3)通过改善交通运营来降低成本。系统设计和操作可以通过更好地适应个人对地点、时刻表规律、里程和其他因素的偏好来提高驾驶员满意度，同时还可以改善对所有利益相关者都重要的经济措施。系统开发将按照围绕三个集成分析组件的框架构建的面向系统的方法进行。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，以确定影响卡车运营和周转的因素以及他们的量化贡献），2)预测性（将这些数据应用于设计新的数据驱动的周转预测模型在新的协作调度范式的背景下），3)规定性（通过优化和仿真框架设计最优中继和点对点网络，该框架结合协同调度/数据驱动的周转预测，并考虑运营成本（如空载重新定位）以及数据驱动周转预测模型获得的周转成本）分析方法。