Data intelligence and risk analytics
| Date | 23 January 2020 |
| Pages | 249-252 |
| DOI | https://doi.org/10.1108/IMDS-02-2020-606 |
| Published date | 23 January 2020 |
| Author | Desheng Dash Wu |
| Subject Matter | Information & knowledge management,Information systems,Data management systems,Knowledge management,Knowledge sharing,Management science & operations,Supply chain management,Supply chain information systems,Logistics,Quality management/systems |
Guest editorial
Data intelligence and risk analytics
Data intelligence and risk analytics develop dramatically in recent years. However, the
relevant research work is still lack of attention. The purpose of this special issue is to
innovativeresearch methodologiesfrom the perspective of data intelligenceand risk analytics.
Data intelligence is the analysis of various forms of data in such a way that it can be used
by companies to expand their services or investments (Waller and Fawcett, 2013). Data
intelligence is used widely in lots of fields, such as O2O service (He et al., 2016),
recommendation system (Pan et al., 2019), energy system (Wen et al., 2019; Xiao et al., 2018),
supply chain fields (Corbett and de Groote, 2000; Wu et al., 2019), forecasting management
(Yu et al., 2008; Zhang et al., 2009), machine learning (Abadi et al., 2016; Wu and Dash Wu,
2019) and risk identification (Wu and Chen, 2017). The risk exists on many aspects in
managemental and economic insights (Chod, 2016; Tang et al., 2017) and so on. Risk
analytics combined with data intelligence will provide a brand-new perspective to facilitate
industry and society development. However, such massive and invaluable data from risk
analytics may bring new challenges such as data processing, data visualization, data-driven
decision models, risk decision support systems, etc., in the era of big data.
This special issue of Industrial Management & Data Systems contains 11 research
papers. These papers focus on recent advances topics of data intelligence and risk analytics
including quay crane (QC) scheduling problem, forecasting of supply chain sales, food
safety risks, credit risk assessment, risk of battery accidents, the entrepreneurial team’s
adaptability in risk decision-making process, risk of the marketplace channel strategy,
ordering decision for capital-constraint retailers with risk-averse preference and bankruptcy
threshold, forecast on interval-valued exchange rate, lead-lag relationship between investor
attention and the stock price, and the public attention to the accident.
The work by He et al. addresses QC scheduling problem for multiple hatches vessel
considering double-cycling strategy. This paper formulates a mixed integer programming
model considering realistic operational constraints, where a novel objective is proposed to
maximize the number of dual-cycle operations of QCs in the whole process. The proposed
model also provides approach to realize the trade-off between energy cost and operation
efficiency in the double-cycling problem. A series of numerical experiments validate the
proposed model, and the results analysis demonstrates the proposed approach can promote
the number of double-cycling in the handling process of a vessel. This work can help
improving the operational efficiency and reduce the delay risk of a vessel departure.
The work by Weng et al. proposes a new model based on LightGBM and LSTM to
forecast the supply chain sales. First, the paper shows the process of data analysis and data
feature extraction in a visual way. Next, the paper uses LSTM model to extract high-level
time series feature from data and combines it with other sale features, then uses them as
input to the LightGBM model to forecast sales. Finally, three raw sales data sets are used to
evaluate the performance of the model. The result shows the combined model can forecast
supply chain sales with high accuracy and strong interpretability which is suitable for
industrial production environment.
The paper by Wang et al. establishes the microbial growth model to identify the
characteristics of food safety risks. Benchmark functions and numerical experiments
examine the performance of algorithm, which can improve the efficiency of cold chain
distribution and reduce distribution costs. This work finds that the established model and
algorithm are effective to control the risk of perishable food in distribution process.
Industrial Management & Data
Systems
Vol. 120 No. 2, 2020
pp. 249-252
© Emerald PublishingLimited
0263-5577
DOI 10.1108/IMDS-02-2020-606
249
Guest editorial
To continue reading
Request your trial