Improving Data Quality for LCC Prediction Using Cloud Computing
The aim of the project IDQfLCC project is to:
Develop a framework for data quality analytics of MAXIMO database, the framework covers three essential aspects: diagnostic, prediction and prescription.
Develop, validate and demonstrate an economic replacement time (ERT) decision model in the mining environment.
Build a generic software considering real operational parameters as a prototype demonstration in mining operational environment.
The challenge of generalizing Data Quality assessment is hindered by the fact that Data Quality requisites depend on the purpose for which the data will be used and on the subjectivity of the data consumer. The approach proposed in this paper to address this challenge is to employ a semi-automated user-guided Data Quality assessment. This paper introduces a generic framework for data quality analytics which is mainly composed by a set of software units to perform semi-automated Data Quality analytics and a set of Graphical User Interfaces to enable the user to guide the Data Quality assessment. The framework has been implemented and can be customized according to the needs of the purpose and of the consumer. The framework has been instantiated in a case study on Long-hole drill rigs, where several Data Quality issues have been discovered and their root cause investigated
@article{castano2020generic,title={A generic framework for data quality analytics},author={Casta{\~n}o Arranz, Miguel and Gustafson, Anna and Al Chalabi, Hussan},journal={COMADEM International},volume={23},number={1},year={2020},publisher={COMADEM}}
