The Data Analytics Blog

Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.

All Posts

How Machine Learning Is Helping Call Centres Improve Their CX

October 29, 2019 at 3:07 PM

The call centre world, unsurprisingly, ranks as one of the highest adopters of data analytics platforms year on year. This is largely due to the invaluable insights we gain through the analysis of thousands of calls received each day by the typical call centre. With speed being of the essence in making the right decision at the right time for each caller many call centres are turning to machine learning to automate their data analysis and make crucial customer experience decisions within seconds.

Watch our video to meet Agent X, the call centre virtual assistant to solve your call centre agents' problems. 

Reducing call duration and increasing first call resolutions

Whether you’re running an inbound or outbound contact centre, the interactions between your company representatives and your customers is a crucial area for customer success. Thanks to machine learning algorithms, businesses are able to manage those customer-facing moments more efficiently. According to, “Emotion analysis through text and speech analytics can paint a more complete picture when combined with the overall first call resolution (FCR) metric, indicating the level of confidence customers feel about whether the answer they received has resolved the issue at hand.”

New to Machine Learning? Read our blog post What is Machine Learning?

Machine learning algorithms are also helping customers reach the right representative in a shorter space of time (and alleviating much of their frustration in the process) by smartly routing calls based on their nature to the right person with the appropriate knowledge and skill-level. This, in turn, reduces call duration periods, repeat calls or call abandonment rates by unhappy callers. On-screen prompts based on the machine learning analyses of callers’ moods, or other indicators, are also allowing contact centre agents to more effectively deal with customer queries or problems and reduces the need for customers to make often frustrating repeat calls to the business.

Machine Learning to determine the right time and number to call can be used in call centres for both sales to reach prospects and debt collection to reach debtors. 

Download our guide to using machine learning in business, where we explore how you can use machine learning to better tap into your business data and gain valuable, informing insights to improve your business revenue. 

Reducing call volumes and increasing customer satisfaction

Machine learning can be used to reduce call volumes by eliminating the need for customers to call when there is, for example, a network fault for a telecommunications company / ISP or reception issues with a satellite company. By analysing voice / speech patterns, emotions and words from incoming calls, machine learning can identify 1) that there is a an issue (anger or irritation based on tone of voice), 2) what the issue might be (“slow line speed” or “no reception”) and 3) where it might be (based on the caller’s location). By analysing an influx of calls coming in and identifying these types of patterns, machine learning could kick off a notification to technical support to notify them of the issue and enable the contact centre to send out a pre-emptive SMS / email / WhatsApp to all subscribers in the affected area or post a message on Twitter / Facebook to let them know that they are aware of the issue and are working on having it resolved.

Increasing revenue by seizing sales opportunities

To serve the customer better – and boost profits in the process – businesses need to make smart decisions on the fly. Direct interchanges between consumers and call centres are golden opportunities to make this happen. According to John Magliocca, chief consultant for contact centre services outsourcing company, ISG, “There have been efforts underway to put contact data to work to best understand the current mood of the customer and other information that can immediately mould client strategy and direction [for some time].”  With volumes of customer and transaction data available, machine learning platforms can inform contact centre staff on ideal product suggestions based on past purchases or upgrade a subscription service to premium if a customer’s financial situation has changed. Data-driven solutions will continue to inform customer insights while simultaneously helping business raise bottom lines.

Machine learning will require user buy-in

Although machine learning can enrich the customer experience considerably, it would have little impact on productivity, profitability or customer satisfaction levels without buy-in from the people intended to use it. Forrester advises business leaders who want to adopt new technology platforms as a means to improve the customer experience, “Senior executives set the tone for the need for a customer-centric culture and new processes and tools that support customers more effectively. Leaders must plan for changes in the work practices needed to meet customer management goals” . This means involving users in new technology implementations that will ultimately add value to the workforce and importantly, the customer.

Keen to improve your the customer experience in your call centre environment? Find out more about our call centre virtual assistant which uses artificial intelligence/machine learning to deliver relevant data-driven insights to agents about a customer, account holder or prospect during a call.

Using machine learning in business - download guide

Latest Posts

Solving the Credit Unaware Challenge with Psychometrics

At Principa, we engage with clients and organisations across the entire credit lifecycle and track the focus of the South African credit industry. For nearly ten years the focus has consistently been in the collection space, but recently (since early 2021) this has changed and a large number of our clients are focused on acquisitions and originations.

Predicting Customer Behaviour (PART 2)

In Part One of this two-part blog, we started providing a short overview of just some of the propensity models that Principa has developed. In this Part Two, we continue to look at different types of propensity models available across the customer engagement lifecycle that are used to predict behaviour and solve business problems. 

PART 2: How to Cure the Post Pandemic “Collections” Symptoms

In PART 1 of this two-part series, we explored how the current socio-economic climate resulting from the lingering financial hangover caused by the pandemic is negatively impacting the consumer's ability to settle a debt.