Predictive Analytics and Consumer Loyalty
Using big data to target brand success and build equity has become valuable. Review the results of this predictive analysis research and assess how the loyalty rules were derived from this model. Was the classification of the consumers predictive or reflective?
Research objectives
-
Customers value was Analyzed by segmenting them according to the new approach TFM and then determine, the level of loyalty for each segment in a big data environment in telecom.
-
A set of features was derived from the telecom data.
-
The best behavioral features for customers with their demographic information were Chosen, based on these features and the level of loyalty for each segment, the following classification algorithms were applied and the classification models were built: random forest classifier, Decision tree classifier, Gradient-boosted tree classifier, and Multiplexer perceptron (MLPC).
-
These models were evaluated based on several criteria that evaluated and selected the most accurate model.
-
The loyalty rules were derived from this model, these rules showed the characteristics of each level of loyalty and thus the loyalty reasons were identified in each segment to target them in a representative manner. The other advantage of classification algorithms application was building a model to classify new users by loyalty.