Discovering Customer Journey Maps using a Mixture of Markov Models

Details

Ressource 1Download: bernard2017Markov.pdf (896.68 [Ko])
State: Public
Version: author
Serval ID
serval:BIB_500C560C6E68
Type
Proceedings: the proceedings of a conference.
Collection
Publications
Institution
Title
Discovering Customer Journey Maps using a Mixture of Markov Models
Publisher
SIMPDA2017
Organization
IFIP 2.6 International Symposium on Data-Driven Process Discovery and Analysis
Address
Neuchatêl, Switzerland
Issued date
12/2017
Editor
Harbich Matthieu, Bernard Gaël, Berkes Pietro, Garbinato Benoît, Andritsos Periklis
Number of pages
5
Abstract
Customer Journey Maps (CJMs) summarize the behavior of customers by displaying the most common sequences of steps they take when engaging with a company or product. In many practical applications, the challenge lies in automatically discovering these prototypical sequences from raw event logs for thousands of customers. We propose a novel, probabilistic approach based on a mixture of Markov models and show it can reliably extract CJMs with just one input parameter (and potentially none).
Keywords
markov models, customer journey mapping, event logs, customer journey analytics
Create date
12/01/2018 14:57
Last modification date
21/08/2019 6:09
Usage data