Resources
-
Tutorials
-
User guide
-
Case studies
- Production optimisation through feedback analysis
- Satisfaction questionnaire analysis
- Health trajectory analysis
- Biocomputing transcriptome analysis
- Risk analysis and security policy
- Difficult intubations analysis
- Cyber-crimes detection
- Customer characterization
- Organization name identification
- Implementation of a Bayesian score
- Modeling and simulation of dynamic systems
- Analysis of a perfume market
- Consumer segmentation
- Identifying drivers of liking
- Salmonella isolation
- Political Analysis
- Studying consumer drivers
- Employees satisfaction analysis
www.bayesia.com does not fully support your browser (Internet Explorer 6).
We suggest upgrading to IE 7 or downloading Firefox for a more enjoyable web experience.
We suggest upgrading to IE 7 or downloading Firefox for a more enjoyable web experience.
Consumer segmentation
We present here how to use BayesiaLab for the segmentation of customers described by a Usage and Attitude survey. We used here what we call the "hierarchical clustering" workflow. This workflow consists in:
- Unsupervised learning to discover all the direct probabilistic relations that hold between the variables
- Variable clustering based on the Kullback-Leibler divergences (non linear measure) corresponding to each arc discovered during unsupervised learning
- Factor induction to create the latent variables corresponding to each identified cluster of variables
- Clustering of the customers based on their descriptions with the induced Factors
- Supervised learning to find the best characterization of the segmentation in terms of Manifest variables
This work has been realized in collaboration with Repères.
Download article