Is Predictive Modeling Key to Understanding Customer Loyalty?
Published on: 7th Dec 2006
Note -- this news article is more than a year old.
The introduction of Mobile Number Portability into a market generally ensures that customer retention is at the top of mobile operators' agendas. The South Africa based marketing insight services company Knowledge Factory argues that predictive modelling techniques are the key to understanding what drives customer loyalty.
Some analysts suggest that more than a quarter of consumers (27 percent) will change networks within a year of the MNP becoming available in South Africa and predictions like this have ensured that customer retention is firmly at the top of the agenda for mobile operators.
"MNP will definitely have an impact and create volatility in the telecoms market," confirms Suben Moodley, client services manager at leading marketing insight services company, Knowledge Factory, "but it will simply be an expansion or increase of existing churn propensities."
Moodley acknowledges that, without the artificial hook of losing their number, customers will feel less trapped, but argues that it will be existing grievances that prompt them to switch providers. "The higher rates of churn will predominantly reflect customers with old gripes or prior reasons for wanting to move taking advantage of MNP," he maintains.
Although particularly rife in fiercely competitive industries like telecoms, customer churn is a significant problem that spares very few organisations. "So the real question, whether you are a mobile operator facing MNP or not, is what effect is churn having on your business day-in, day-out," contends Moodley.
What drives churn in telecoms?
The mobile communications industry is very product driven and price conscious, two traditional reasons for customer churn, but Moodley suggests that the main driver of churn is service delivery, both in terms of customer service and network performance.
"Although it might appear differently, with price conscious customers clamouring for the latest and greatest handsets, these reasons tend to cancel themselves out in this age of hyper-consumerism," explains Moodley. "Products and service packages are quickly replicated by the competition so there is no real, enduring advantage from either."
Uncovering churn patterns
To help organisation's effectively manage their churn, Knowledge Factory uses predictive modelling techniques based on sound empirical evidence and strong analytics. "It's actually highly transparent," observes Moodley, "we take a firm's customer transaction data and then apply sophisticated mathematical models to uncover the churn patterns within it."
By designing and combining a wide variety of mathematical techniques, including artificial neural networks, statistical regression and decision trees, the company can determine the propensity of any individual customer to cease doing business with an organisation within a given time period.
"The results are often quite surprising," notes Moodley, "you might be under the impression that customers want the latest phones or trendier outlets, but a large number of those leaving your network might have experienced a considerable number of dropped calls in the last six months."
Strategies need action
"Once we have discovered the reasons behind the churn you are experiencing, we can use them to devise analytical customer management strategies," explains Moodley. "This is because sophisticated predictive churn models on their own are not enough and organisations need to create informed strategies from them."
Reiterating the importance of creating and implementing customer management strategies, Moodley notes that "interesting results won't change anything and companies must be prepared to action the strategies we help them devise to really tackle churn."
Mining your gold
Nonetheless, Moodley argues that analytical customer management strategies are ideal for mobile phone operators because they have unusually rich customer transactional data, which allows very specific patterns and results to be identified.
"Many operators have recognised this and made significant investments in churn modelling software," observes Moodley, "but they still struggle to get maximum value from their data because of the expertise required."
He cites using the data to up and cross sell customers as another example, aside of reducing churn, of how mobile operators should be 'mining their gold'.
"In the end, MNP represents a tremendous opportunity for operators," concludes Moodley. "Armed with our market-leading customer churn modelling techniques and expertise, operators can not only ensure they mitigate churn, but take advantage of the volatility for acquisition ? making sure that any customers that do move, move to them."