Data mining-based dispatching system for solving the local pickup and delivery problem

The Local Pickup and Delivery Problem (LPDP) has drawn much attention, and optimization models and algorithms have been developed to address this problem. However, for real world applications, the large-scale and dynamic nature of the problem causes difficulties in getting good solutions within acceptable time through standard optimization approaches. Meanwhile, actual dispatching solutions made by field experts in transportation companies contain embedded dispatching rules. This paper introduces a Data Mining-based Dispatching System (DMDS) to first learn dispatching rules from historical data and then generate dispatch solutions, which are shown to be as good as those generated by expert dispatchers in the intermodal freight industry. Three additional benefits of DMDS are: (1) it provides a simulation platform for strategic decision making and analysis; (2) the learned dispatching rules are valuable to combine with an optimization algorithm to improve the solution quality for LPDPs; (3) by adding optimized solutions to the training data, DMDS is capable to generate better-than-actuals solutions very quickly.

[1]  Amelia C. Regan,et al.  Local truckload pickup and delivery with hard time window constraints , 2002 .

[2]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[3]  J. Wesley Barnes,et al.  Solving the Pickup and Delivery Problem with Time Windows Using Reactive Tabu Search Transportation , 2000 .

[4]  Ian H. Witten,et al.  Data mining - practical machine learning tools and techniques, Second Edition , 2005, The Morgan Kaufmann series in data management systems.

[5]  R B D'Agostino,et al.  A comparison of logistic regression to decision-tree induction in a medical domain. , 1993, Computers and biomedical research, an international journal.

[6]  Jacques Desrosiers,et al.  The Pickup and Delivery Problem with Time Windows , 1989 .

[7]  K. Fagerholt,et al.  A travelling salesman problem with allocation, time window and precedence constraints — an application to ship scheduling , 2000 .

[8]  J. Desrosiers,et al.  Methods for routing with time windows , 1986 .

[9]  Andrew Lim,et al.  Multi-depot vehicle routing problem: a one-stage approach , 2005, IEEE Transactions on Automation Science and Engineering.

[10]  Clyde W. Holsapple,et al.  A machine learning method for multi-expert decision support , 1997, Ann. Oper. Res..

[11]  Warren B. Powell,et al.  An Adaptive Dynamic Programming Algorithm for the Heterogeneous Resource Allocation Problem , 2002, Transp. Sci..

[12]  Zhi-Long Chen,et al.  Solving a Practical Pickup and Delivery Problem , 2003, Transp. Sci..

[13]  Theodora A. Varvarigou,et al.  Application of Genetic Algorithms to a Large-Scale Multiple-Constraint Vehicle Routing Problem , 2003, Int. J. Comput. Intell. Appl..

[14]  Michel Gendreau,et al.  Vehicle Routing Problem with Time Windows, Part II: Metaheuristics , 2005, Transp. Sci..

[15]  Hiroshi Motoda,et al.  Feature Extraction, Construction and Selection , 1998 .

[16]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[17]  Michel Gendreau,et al.  Vehicle Routing Problem with Time Windows, Part I: Route Construction and Local Search Algorithms , 2005, Transp. Sci..

[18]  Martin W. P. Savelsbergh,et al.  Efficient Insertion Heuristics for Vehicle Routing and Scheduling Problems , 2004, Transp. Sci..

[19]  Andrew Lim,et al.  A Transportation Problem with Minimum Quantity Commitment , 2006, Transp. Sci..

[20]  Sean Ekins,et al.  Application of data mining approaches to drug delivery. , 2006, Advanced drug delivery reviews.

[21]  W. Loh,et al.  LOTUS: An Algorithm for Building Accurate and Comprehensible Logistic Regression Trees , 2004 .

[22]  Leyuan Shi,et al.  Hybrid Nested Partitions and Mathematical Programming Approach and Its Applications , 2008, IEEE Transactions on Automation Science and Engineering.

[23]  Warren B. Powell,et al.  Dynamic Control of Logistics Queueing Networks for Large-Scale Fleet Management , 1998, Transp. Sci..

[24]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[25]  Hiroshi Motoda,et al.  Feature Extraction, Construction and Selection: A Data Mining Perspective , 1998 .

[26]  Leyuan Shi,et al.  Nested Partitions Method for Global Optimization , 2000, Oper. Res..

[27]  Michael J. Shaw,et al.  Decision support system for scheduling a Flexible Flow System: Incorporation of feature construction , 1998, Ann. Oper. Res..

[28]  Xiaonan Li,et al.  Discovering Dispatching Rules Using Data Mining , 2005, J. Sched..

[29]  Michael J. Shaw,et al.  Intelligent Scheduling with Machine Learning Capabilities: The Induction of Scheduling Knowledge§ , 1992 .

[30]  Tore Grünert,et al.  Local Search for Vehicle Routing and Scheduling Problems: Review and Conceptual Integration , 2005, J. Heuristics.