Discovering Customer Journey Maps using a Mixture of Markov Models
| Přispěvatelé: | Harbich, Matthieu (ed.), Bernard, Gaël (ed.), Berkes, Pietro (ed.), Garbinato, Benoît (ed.), Andritsos, Periklis (ed.) |
|---|---|
| Rok vydání: | 2017 |
| Předmět: | |
| Popis: | 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). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|