Xia Li, Ruibin Bai, Peer-Olaf Siebers and Christian Wagner
Many transport and logistics companies nowadays use raw vehicle GPS data for travel time prediction. However, they face difficult challenges in terms of the costs of information…
Abstract
Purpose
Many transport and logistics companies nowadays use raw vehicle GPS data for travel time prediction. However, they face difficult challenges in terms of the costs of information storage, as well as the quality of the prediction. This paper aims to systematically investigate various meta-data (features) that require significantly less storage space but provide sufficient information for high-quality travel time predictions.
Design/methodology/approach
The paper systematically studied the combinatorial effects of features and different model fitting strategies with two popular decision tree ensemble methods for travel time prediction, namely, random forests and gradient boosting regression trees. First, the investigation was conducted using pseudo travel time data that were generated using a pseudo travel time sampling algorithm, which allows generating travel time data using different noise processes so that the prediction performance under different travel conditions and noise characteristics can be studied systematically. The results and findings were then further compared and evaluated through a real-life case.
Findings
The paper provides empirical insights and guidelines about how raw GPS data can be reduced into a small-sized feature vector for the purposes of vehicle travel time prediction. It suggests that, add travel time observations from the previous departure time intervals are beneficial to the prediction, particularly when there is no other types of real-time information (e.g. traffic flow, speed) are available. It was also found that modular model fitting does not improve the quality of the prediction in all experimental settings used in this paper.
Research limitations/implications
The findings are primarily based on empirical studies on limited real-life data instances, and the results may lack generalisabilities. Therefore, the researchers are encouraged to test them further in more real-life data instances.
Practical implications
The paper includes implications and guidelines for the development of efficient GPS data storage and high-quality travel time prediction under different types of travel conditions.
Originality/value
This paper systematically studies the combinatorial feature effects for tree-ensemble-based travel time prediction approaches.
Details
Keywords
Atanu Chaudhuri, Iskra Dukovska-Popovska, Nachiappan Subramanian, Hing Kai Chan and Ruibin Bai
The purpose of the paper is to identify the multiple types of data that can be collected and analyzed by practitioners across the cold chain, the ICT infrastructure required to…
Abstract
Purpose
The purpose of the paper is to identify the multiple types of data that can be collected and analyzed by practitioners across the cold chain, the ICT infrastructure required to enable data capture and how to utilize the data for decision making in cold chain logistics.
Design/methodology/approach
Content analysis based literature review of 38 selected research articles, published between 2000 and 2016, was used to create an overview of data capture, technologies used for collection and sharing of data, and decision making that can be supported by the data, across the cold chain and for different types of perishable food products.
Findings
There is a need to understand how continuous monitoring of conditions such as temperature, humidity, and vibration can be translated to support real-time assessment of quality, determination of actual remaining shelf life of products and use of those for decision making in cold chains. Firms across the cold chain need to adopt appropriate technologies suited to the specific contexts to capture data across the cold chain. Analysis of such data over longer periods can also unearth patterns of product deterioration under different transportation conditions, which can lead to redesigning the transportation network to minimize quality loss or to take precautions to avoid the adverse transportation conditions.
Research limitations/implications
The findings need to be validated through further empirical research and modeling. There are opportunities to identify all relevant parameters to capture product condition as well as transaction data across the cold chain processes for fish, meat and dairy products. Such data can then be used for supply chain (SC) planning and pricing products in the retail stores based on product conditions and traceability information. Addressing some of the above research gaps will call for multi-disciplinary research involving food science and engineering, information technologies, computer science and logistics and SC management scholars.
Practical implications
The findings of this research can be beneficial for multiple players involved in the cold chain like food processing companies, logistics service providers, ports and wholesalers and retailers to understand how data can be effectively used for better decision making in cold chain and to invest in the specific technologies, which will suit the purpose. To ensure adoption of data analytics across the cold chain, it is also important to identify the player in the cold chain, which will drive and coordinate the effort.
Originality/value
This paper is one of the earliest to recognize the need for a comprehensive assessment for adoption and application of data analytics in cold chain management and provides directions for future research.