Importance of Predicting Customer Churn The ability to predict that a particular customer is at a high risk of churning, while there is still time to do something about it, represents a huge additional potential revenue source for every online business. Besides the direct loss of revenue that results from a customer abandoning the business, the costs of initially acquiring that customer may not have already been covered by the customers spending to date. (In other words, acquiring that customer may have actually been a losing Investment. )
Furthermore, It Is always more difficult and expensive to acquire a new customer than It Is to retain a current paying customer. Reducing Customer Churn with Targeted Proactive Retention In order to succeed at retaining customers who would otherwise abandon the business, marketers and retention experts must be able to (a) predict in advance which customers are going to churn and (b) know which marketing actions will have the greatest retention impact on each particular customer. Armed with this knowledge, a large proportion of customer churn can be eliminated.
While simple in theory, the realities involved with achieving this “proactive retention” goal are extremely challenging. The Difficulty of Predicting Churn Churn prediction modeling techniques attempt to understand the precise customer behaviors and attributes which signal the risk and timing of customer churn. The accuracy of the technique used is obviously critical to the success of any proactive retention efforts. After all, If the marketer Is unaware of a customer about to churn, no action will be taken for that customer.
Additionally, special retention-focused offers or incentives may be inadvertently provided to happy, active customers, resulting in reduced revenues for no good reason. Unfortunately, most of the churn prediction modeling methods rely on quantifying risk based on static data and metrics, I. E. , information about the customer as he or she exists right now. The most common churn prediction models are based on older statistical and data-mining methods, such as logistic regression and other binary modeling techniques.
These approaches offer some value and can identify a certain percentage of at-risk customers, but they are relatively inaccurate and end up leaving money on the table. Customer churn for a major bank The credit card division of a major bank were facing some disturbing trends, these were: An increasingly competitive credit card business environment A shrinking number of customers within their credit card customer base A high proportion of the customers being lost were very profitable TOT maintain the viability of the company’s credit card offering, action was required to address these disturbing trends.
The key objectives of this project were to ensure that our client reduced churn amongst valuable credit card customers and to utilities our clients retention team in the most efficient and effective manner. By using a range of advanced statistical modeling and dynamiting techniques Teaming enabled our client to accurately identify customers who were about to leave. Our client then targeted the customers identified as likely to churn in the near future with an offer they Just could not refuse!
The customers saved by this process made a direct contribution to bolstering our clients’ bottom nine. Supply Chain, or no Supply Chain? So does this ring the death knell for the supply chain managed approach to procurement of loss adjusters? Probably not. The levels of customer carnage indicate, in the I-J at least, that the customer has a minimum level of expectation of the service they will receive during a claim. It is because of this minimal level of expectation that the policyholder is likely to continue their purchasing decisions based principally on cost.
In a crowded insurance marketplace where supply exceeds emend, insurers will continue to offer competitive premium pricing. This will be backed up by higher precision underwriting through customer and location intelligence. So as premium pricing remains tight, and investment income by insurers runs the real risk of being threatened by an economic downturn, the pressure will fall back on the claims process. No change there then. And that means harder and more robust procurement processes throughout the supply chain, including the selection of adjusters.
The most successful adjusters and adjusting rims going forward will inevitably need to take a more broader view of what they offer, and their true value. This may involve the creation of new metrics that go beyond the traditional ‘claim and adjustment’ calculation, but also measure (and perhaps seek reward on) the behavior of the customer after the claim has been resolved. How might this reflect on the adjustment of the loss, if one of the key drivers is that of keeping the customer satisfied? Perhaps the ‘new adjuster’ needs to be rewarded on a commission basis, linked to customer retention?
