Skip to Main content Skip to Navigation
Conference papers

Mining Customer-related Data to Enhance Home Delivery in E-commerce: an experimental study

Abstract : In a B2C e-commerce environment, home delivery service refers to delivering goods from an e-retailer’s storage point to a customer’s home. High rate of failed delivery due to the customer’s absence causes significant loss of logistics efficiency. This paper aims to study innovative solutions to the problem, such as data-related techniques. This paper proposes a methodological approach to use customer-related data to optimize home delivery. The idea is to estimate the attendance probability of a customer via mining his electricity consumption data, in order to improve the success rate of delivery and optimize transportation. Computational experiments reveal that the proposed approach could reduce the total distance from 3% to 20%, and theoretically increase the success rate around 18%-26%. Being an experimental study, this paper demonstrates the effectiveness of data-related techniques or data-based solutions in home delivery problem, and provides a methodological approach to this line of research.
Document type :
Conference papers
Complete list of metadata
Contributor : Shenle Pan Connect in order to contact the contributor
Submitted on : Tuesday, May 24, 2016 - 3:51:30 PM
Last modification on : Thursday, May 12, 2022 - 7:30:05 AM


  • HAL Id : hal-01320962, version 1


Shenle Pan, Han Yufei, Bin Qiao, Etta Grover-Silva, Vaggelis Giannikas. Mining Customer-related Data to Enhance Home Delivery in E-commerce: an experimental study. 6th International Conference on Information Systems, Logistics and Supply Chain (ILS2016), Jun 2016, Bordeaux, France. ⟨hal-01320962⟩



Record views