Prototype model for big data predictive analysis in logistics area with Apache Kudu

Abstract

Logistics is area, which is evolving rapidly, generating a lot of data lately. There are several problems that, even when partially digitized, require additional work. At the same time there is a need of big data analyses. These analyses are represented by machine learning and statistical analyses. One important problem is these with missing data for delivery in the whole process of transportation, other is about empty freight transportation. The purpose of this paper is to present an ICT prototype model with analytical tool Apache Kudu in logistics area, which will contribute to resolve such problems in area. Content analysis and systematic approach are used. Statistical methods and statistical data are used. Growth rates of empty road transport are calculated. The presented data are for Bulgaria and its neighbour’s county, excluding Romania, because of the missing data. Croatia is also included in the analysis. Growth rate analysis indicates problems with empty fright transport in some countries. The tendency for Bulgaria is to reduce empty road freight transport, even though it is better for logistics organizations to work for optimizing the process of delivery.

Keywords

• logistics
• machine learning
• big data
• big data analyses
• predictive analysis
• apache kudu
• apache hadoop
• logistics software
• growth rates