I’m in a CRM project at a Telco company and I am in charge of retention, I would like to know what kinds of retention campaigns you have used for your clients so that I have a better idea of real experiences implemented to make a better decision about which one I should apply.
Years ago I work implementing a retention model in the telco I was working. The retention model was a Logistic regression with very good accuracy. Now, in my opinion the problem of retention have many faces, it is not only “who’s is going to leave you”, it is also when is going to leave you and what efforts you should make on them. I think is a 3 dimension problem, you have to know:
1-) Who’s leaving?
2-) When’s leaving?
3-) Is worth the effort of retention?
I will recommend you to use a Logistic regression or a decision tree or any traditional model to find who is going to leave, after that, you should implement a survival analysis to determine when is going to leave, and finally, you should have an idea of the time value of the customer to size the effort of retention.
You should not underestimate also you effort on fidelity.
I`ll start first with retention campaign definition:
1.it is for a customer you currently have
2. which you target with specific product
3. and campaign is executed thru specific channel
Customer (or group of customers) you choose to be part of the campaing based on a specific characteristics ... it could be age, wealth, behavior the info you get from BI or provisioning system to strip something specific from data.
Product ... is based mostly on your product portfolio with such a discount to make deal easier to catch. Product is based on usage and behavior of the customer.
Channel ... since everything need to lead to a deal channel selection to get in contact with customer should be chosen wisely, based also on complexity of the product.
Retention is much important than gaining new customers, but currently not able to provide numbers on it.
There are early warning signals that customer you have is preparing to move away diminished usage or increased last few months etc. such deviation in behavior. The customers who are with for many years would be happy also to get something better, but what I`d seen is that ones who are ready to move are most probably a target for such campaigns, the others will stay for you :-)
Retention is considered in my view as a critical capability of any organization who has a objective to grow revenue and reduce input cost.I have recenetly worked with a Telecommunication company in South Africa with a large African footprint on a similar campaign.What i can share with you is below .
-Identify your market
-Understand and Analyse your Average Revenue Markers
-Clarify constrains etc budgets and legislation’s
-Identify strategic partnerships to drive objectives
-Open communication systems
-Manage project traction etc movement via social media and legacy channels
-Involve Department Management
-Document progress for ROI purposes
Most of all have fun and keep it simple .
My example :
I proposed a strategy where customers who where not using there simcards could earn a bonus thru our loyalty plan for loading airtime of more then ZAR 60 and not less the ZA15 over a 4 weeks period the campaign was implemented over 6 months .
The end result increase in prepaid revenue by 60% .Reduction on non calling sim activity of 58%
Your questions is very broad. It’s often helpful to think about churn as either active (those who call in to cancel) or passive (those who stop using the service or reduce their use), and which processes are needed to predict and detect such churn, what actions and propositions can help prevent churn and/or win back or reactivate customers.
Use root cause analysis and analytics to help make the problem more concrete. The details of your campaigns will then need to be guided by CLV analysis and the effectiveness of your retention/save channels. Send me a private message if you want to follow up.
This will mark this comment as best reply and close your question.
Are you sure?
This will close your question without a Best reply.
Are you sure?
This will report this content as inappropiate to the moderators.
Are you sure?