The paper proposes an advanced Multilevel Analytics Model –MAM-, applied on a specific case of study referring to a research project involving an industry mainly working in roadside assistance service (ACI Global S.p.A.). In the first part of the paper are described the initial specifications of the research project by addressing the study on information system architectures explaining knowledge gain, decision making and data flow automatism applied on the specific case of study. In the second part of the paper is described in details the MAM acting on different analytics levels, by describing the first analyzer module and the second one involving data mining and analytical model suitable for strategic marketing e business intelligence –BI-. The analyzer module is represented by graphical dashboards useful to understand the industry business trend and to execute main decision making. The second module is suitable to understand deeply services trend and clustering by finding possible correlations between the variables to analyze. For the data mining processing has been applied the Rapid Miner workflows of K-Means clustering and the Correlation Matrix. The second part of the paper is mainly focused on analytical models representing phenomena such as vehicle accidents and fleet car sharing trend, which can be correlated with strategic car services. The proposed architectures and models represent methodologies and approaches able to improve strategic marketing and –BI- advanced analytics following ‘Frascati’ research guidelines. The MAM model can be adopted for other cases of study concerning other industry applications. The originality of the paper is the scientific methodological approach used to interpret and read data, by executing advanced analytical models based on data mining algorithms which can be applied on industry database systems representing knowledge base.
Innovative BI approaches and methodologies implementing a multilevel analytics platform based on data mining and analytical models: a case of study in roadside assistance services
Massaro A;
2019-01-01
Abstract
The paper proposes an advanced Multilevel Analytics Model –MAM-, applied on a specific case of study referring to a research project involving an industry mainly working in roadside assistance service (ACI Global S.p.A.). In the first part of the paper are described the initial specifications of the research project by addressing the study on information system architectures explaining knowledge gain, decision making and data flow automatism applied on the specific case of study. In the second part of the paper is described in details the MAM acting on different analytics levels, by describing the first analyzer module and the second one involving data mining and analytical model suitable for strategic marketing e business intelligence –BI-. The analyzer module is represented by graphical dashboards useful to understand the industry business trend and to execute main decision making. The second module is suitable to understand deeply services trend and clustering by finding possible correlations between the variables to analyze. For the data mining processing has been applied the Rapid Miner workflows of K-Means clustering and the Correlation Matrix. The second part of the paper is mainly focused on analytical models representing phenomena such as vehicle accidents and fleet car sharing trend, which can be correlated with strategic car services. The proposed architectures and models represent methodologies and approaches able to improve strategic marketing and –BI- advanced analytics following ‘Frascati’ research guidelines. The MAM model can be adopted for other cases of study concerning other industry applications. The originality of the paper is the scientific methodological approach used to interpret and read data, by executing advanced analytical models based on data mining algorithms which can be applied on industry database systems representing knowledge base.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
