A view on the methodology of analysis and exploration of marketing data
Maciej Pondel, Jerzy J. Korczak · Annals of Computer Science and Information Systems · 2017
The paper proposes a methodology for the development of a marketing decision support system using Big Data technology and data mining techniques.The approach was inspired by the CRISP-DM methodology, which is not oriented towards Big Data projects.Therefore, we have modified this methodology with respect to the purpose and technological requirements of the project.The proposed methodology was tested during development of RTOM (Real Time Omnichannel Marketing) project.Project tasks focus on the analysis and exploration of large and heterogeneous data sets.The paper presents the phases of the project implementation according to the extended CRISP-DM methodology, taking into account the specifics of the analysis and exploration processes of large realtime marketing databases.Examples of project steps are also provided to illustrate the approach. I. INTRODUCTIONATA exploration is a process of automatic detection of non-trivial, unknown, and potentially useful relationships, rules, patterns, similarities, or trends in large data sets [1].Generally speaking, the task of exploration is to analyze data and processes it in order to better understand and use it in decision-making processes.Data mining is a multidisciplinary area that integrates a range of research fields such as information systems, databases and warehouses, statistics, artificial intelligence, parallel computing, operational research, visualization, and computer graphics.Exploration systems use a broad range of information and communication technologies, Web technologies, information retrieval methods, and geolocation techniques, as well as signal processing and bioinformatics.In this paper, an approach to development methodology of the analysis and exploration of marketing data is presented, adopted in a Real Time Omnichannel Marketing (RTOM) system.In the project, the data is collected mainly in real time and huge sets of data are processed, with high heterogeneity of data sources, formats, volume, and intensity of inflow.The user of RTOM (manager, marketing analyst, etc.) expects acquisition of non-trivial, new and useful knowledge that can be used in the decision-making process.In addition, the knowledge, extracted from the collected data, should be used automatically in customer communication processes to optimize the selected parameters of business process such as This work was supported by Regional Research Program, Wrocław, Poland.Grant RPDS.01.02.