Analytical methods for tracking customer portrait: intelligent interpretation of CRM philosophy

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

KRIKSCIUNIENE Dalia

Year of publication 2012
MU Faculty or unit

Faculty of Informatics

Citation
Description Analytical methods for tracking customer portrait: intelligent interpretation of CRM philosophy (tutorial): We explore the problem of filling the gap of knowledge existing in the enterprises- how to relate the available information about customer to the desired outcome, expressed in financial terms, such as turnover, profitability, or optimal ordering quantities. The enterprises implement the Customer Relationship Management (CRM) systems in order to improve their performance based on understanding and tracking their customer records. However the important source of inefficiency of CRM systems emanates from ability to select analytic methods of data mining, statistical analysis and forecasting of time series methods, also computational intelligence analysis which can only partially provide some insights about the customer behavior, segmentation or loyalty measurement tasks. The tutorial will introduce the approach of hybrid analysis of customer data by integrating the philosophy of marketing management and intelligent computational analysis. We aim to create classification models for recognizing customer characteristics, explore the causal indicators and their impact for the financial outcome by applying sensitivity analysis. The methods of unsupervised learning, analysis and interpretation of clustering and self-organizing maps results allows to define best fitting customer segments according to their similarity due to compound application of customer portrait characteristics. The dynamics of customer behavior and his migration between the segments affected by different combinations of indicators is explored. The hybrid approach allows enhancing research capabilities by achieving new level of analysis even in case of partially incomplete information.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.