Analytics Transforms a Telecom Company – A Case Study

Thursday 12th, November 2015

It is a truth universally known that Telecom companies have a unique advantage in the modern marketplace as they have more data than any other industry about their customers even up to knowing where a certain customer is at a certain time. Now this is data that they can use – which most of them don’t. Here is a brief account about one company that invested in tools and used them to understand their customer behavior better.

The company

X-Com (name has been changed) is a huge communications service provider handling communications, network and hosted IT services. With a 1000 offices spread over 19,000 miles, they already had software to predict customer churn. But they had a desire to go deeper and understand the reasons behind retention risks and place this insight into the hands of a wider range of employees than before. And so they invested in IBM® SPSS® solutions – this would help them hone their predictive models and build a richer, more up-to-date picture of its client base.

How they went about doing this

First the X-Com Business Intelligence team started out on to build a more robust process around churn analytics. They used the IBM SPSS Modeler to build a second generation of its churn model – the advantage here was that it incorporates additional variables and delivers more accurate results than the earlier version. The SPSS Modeler helped them identify many effective variables, increasing the number it studied by 400 percent, from 150 to 750 and helped them think smarter. Through this, X-Com was able to provide richer information to employees across the organization – they now got a more complete picture of each customer’s situation. They could now move from monthly to weekly analyses – which ensured that everyone had a more up-to-date picture of customers. This in turn made higher-quality business decision-making possible.

X-Com now had access to data from various touchpoints across their business – from sales, CRM and other customer care systems, and external data sources. With this information, they were now able to generate a “churn score” for each customer using predictive analytics. This along with trend data was integrated into a customer information pack that was sent to customer care reps. Accurate churn predictions were now available, which in turn helped customer care reps intervene proactively with customers who had the greatest risk of churning. They could now resolve issues quickly, improve service levels, and ultimately reduce churn and increase retention rates. Information like the likelihood of a customer to churn within the context of other factors such as the churn risk (whether the risk was increasing or decreasing), his purchase history and what recent interactions the company has had with him – was now available with the customer care representatives. They could then understand the whole customer situation in context and were more likely to identify proactive ways to raise satisfaction.

More tools

X-Com also invested in IBM SPSS Analytics Catalyst – which helped them look at large datasets, uncover statistically interesting relationships between variables and present them intuitively. This tool is great for quick, ad-hoc analyses – the results of which could be displayed as graphs that are easy to understand.

Apart from this, they also invested in IBM InfoSphere® BigInsights™ and IBM SPSS Decision Management software. InfoSphere BigInsights helps companies deal with the huge amounts of data flooding into their systems every day – doing text analytics of customer feedback and customer service records, which can then be used to enrich its customer retention model even further.  With there being 300 to 400 variables influencing retention, this tool is great for the company to deal with escalating amounts of data while incorporating new information into its predictive models. The SPSS Decision Management helped X-Com develop business rules that used the scores generated by its predictive models and automatically suggests the best next action to customer care representatives.

They found new ways to extract valuable insights from the masses of customer data available. And by feeding text analytics data into the existing churn model they were able to make even more accurate predictions. The introduction of business rules helped build a more consistent customer service experience.

Business benefits

  • X-Com’ first-generation customer retention model had reduced churn among smaller customers by eight percent in the first year of deployment and a further 18 percent in year two.
  • The ability to identify which customers were in most need of support also enabled X-Com to serve twice as many customers as before without increasing the level of resourcing in its customer care team.
  • The resulting cost-benefits were estimated at savings of $3.8 million per year, which meant that the SPSS Modeler project delivered a full return on investment within just five months.
  • The second-generation model saw a decrease of 142 percent in revenue erosion for the top 20 percent of customers at risk of churning compared to a control group. This translates into an annual saving of more than $10 million.
  • Apart from this X-Com used predictive models to identify opportunities for up- and cross-selling based on a customer’s purchase history and the behavior of other customers with a similar profile.
  • It helped the marketing department as well – by measuring the impact and success of different email campaigns – what make people open particular emails? How can we tailor our campaigns to different customer groups? This enables a more prudent use of marketing budgets – making sure that all interactions with customers are positive – for them and for the company.

likeLike this article(0)

Subscribe to our Newsletter

We collate information around email opening and clicks, using industry standard technologies, to help us monitor and improve our e-newsletter. Please read our Privacy Policy for more information on how we use your data.



Subscribed successfully Thanks for Subscribing