Big Data Based Logistics Data Mining Platform: Architecture and Implementation

Big Data Based Logistics Data Mining Platform: Architecture and Implementation

Fei Gao (School of Economics and Management, Beijing Jiaotong University, Beijing, China) and Qilan Zhao (School of Economics and Management, Beijing Jiaotong University, Beijing, China)
DOI: 10.4018/IJITN.2014100103


With the development of intelligent logistics, enormous amount of logistics data are be-coming one of the sources of big data. Building the logistics information platform with big data mining and analysis capabilities to make full use of the huge logistics data is the inexorable trend for intelligent logistics. This paper studied the characteristics of the logistics big data, then, a big data based logistics data mining platform is designed and implemented by utilizing big data processing and storage techniques. The architecture and functions of the platform will be described in detail. This paper also studied the mining steps and requirements for logistics data mining, which is significant for practical applications.
Article Preview

2. Characteristics Of Logistics Big Data

Big data technologies are developed when it is hard to the deal with the data with too huge volume and complexity for conventional data processing technologies. Currently, there is no a unified definition for big data. In general, big data is referred as the data with huge volume, high variety, changing velocity. Nowadays the global economy’s continuing growth and the development of network technique make logistics information becomes one of the sources of the big data, such as commodity price fluctuations, information of commodities, customers’ reviews and customer behaviors of online shopping sites. Combined with the HACE theory in [2], the characteristics of logistic data can be concluded as following:

In the perspective of data, logistics big data has the characteristics of huge volume, heterogeneous attributes and diverse dimensionality. The ‘huge’ here may not mean the logistic big data occupy a huge storage space, such as TB level. Most of the big data are automatically generated by machines, but most logistics big data are generated by human’s production activities and most of them are organized as structured data or semi-structured data. In many actual applications, the ‘huge’ of big data here means extremely larger amounts of data entries. For example, the daily site visits of America’s Amazonas website is about 15 million and Taobao’s daily site visits is even more striking: about 100million hits. To analysis these logistic data, it doesn’t need very large storage space for the sales record of these websites, but it is impossible without big data processing techniques.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2019): 1 Released, 3 Forthcoming
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing