Aug 2019 - Client churn prediction in R - an overview (Raul Manongdo)
Details
We look forward to seeing you at our next R meetup, on 14th of August.
Arrive from 5:45 pm for a 6 pm talk.
Synopsis:
Predicting client churn is widely acknowledged as a cost-effective way of realising customer life-time. It is claimed that it costs three times more to acquire a new customer than to retain existing ones. The talk will dwell on development of a binary client churn prediction model as a postgraduate research thesis and as applied to a medium-sized service company.
The talk will include:
- Literature review of models used in home care service industry
- Regression, Random Forest and C5.0 decision trees in R as candidate models
- Model comparison and selection in R
- Feature selection techniques and other R packages used
Speaker Bio:
Raul Manongdo – concluded last year his Masters in Analytics by Research at UTS with thesis on applied client churn prediction modelling. Whilst completing his thesis, he worked as a data analyst/research intern for UTS Advance Analytics Institute for its industry engagements and subsequently as a data scientist. He is coming from an extensive database developer/modeller practitioner experience and currently developing BI systems.
His thesis on applied client churn prediction modelling is published at https://opus.lib.uts.edu.au/handle/10453/123179.