Sophisticated text analytics help the company delve deeper into member enquiries and pinpoint areas for improvement

To take its industry-leading customer satisfaction to even greater heights, Nationwide set out to investigate why members get in touch and find better ways to resolve their enquiries.

Strong market position

In recent years, a wave of regulatory changes has ignited fierce competition in the UK banking industry. An influx of new market entrants has given consumers greater choice than ever before, while new rules make it easier for people to switch their current accounts between providers. One of the players to come out strongest from these changes is Nationwide, which gained a million new current-account members last year alone. An important factor attracting people to Nationwide is its award-winning service; Nationwide has a comfortable 4.6 percent lead on the industry’s customer satisfaction index.

Despite its strong position, Nationwide is eager to improve rather than rest on its laurels. In this spirit, the building society set out to investigate why members get in touch, and see if it could find better ways of resolving their queries.

Graeme Reed, Senior Manager of Analytics of Nationwide, remarks: “Our recent growth has put pressure on our contact centre, which now receives over 800,000 calls from members every month. We know that many people call the contact centre if they try and fail to complete a transaction in another channel, so our idea was to investigate how we could improve other channels to reduce call volumes.”

Taking an innovative approach

Many members choose to contact Nationwide via secure emails sent when they are logged into online banking. Nationwide decided to conduct a Proof of Concept (PoC) using sophisticated SAS Text Miner and SAS Contextual Analytics software to understand the types of enquiries it receives via this channel, and look for better ways to manage them.

In the PoC, the analysts identified the root cause of each enquiry, whether the query was resolved, and how many emails were exchanged in the process. Sentiment analysis from the SAS solutions helped Nationwide to detect the member’s mood; for instance, unsurprisingly, analysts identified that people’s moods worsen as the number of emails rises.

Delivering valuable results

From the PoC, Nationwide established that over half of the emails could have been avoided entirely. For example, ten percent of members who sent a secure email mentioned that their transaction had not been resolved first time around in another channel. Another 19 percent of queries were not resolved the first time the member sent a secure email, and a further 26 percent of requests concerned transactions that could be moved to an online digital process. Equipped with this insight, Nationwide is now proactively working to improve other channels to reduce the number of member enquiries.

“Within a short PoC using SAS text analytics to analyse member enquiries, we established several concrete ways to make our service legendary,” explains Graeme Reed. “For example, we discovered that many members contact us because they require proof of the travel insurance they gain through their FlexPlus current account. The documentation is available on our website, but if we make it easier to find, then more people will access it on a self-service basis. In another example, we found that members contacted us asking for a paper statement, because our online statements did not contain sufficient personal information to function as proof of address. By tweaking the statement format, we can eliminate these requests. Furthermore, if several members contact us about transactions that cannot be completed online, we can consider building a digital capability to meet their needs.

“In total, by guiding more members towards digital channels and avoiding unnecessary enquiries, we identified significant inefficiencies from the secure emails alone. We can reinvest the savings generated by improving these processes in other products and services.”

Building a brighter future

Following the fruitful results of the PoC, Nationwide plans to bring text analytics into production in early 2019. Specifically, Nationwide plans to deploy SAS Visual Text Analytics software, which incorporates SAS Text Miner and SAS Contextual Analytics software and runs on the next-generation SAS Viya platform.

“We are currently deploying SAS Viya to take our analytics capabilities to the next level and to complete straightforward tasks such as ad-hoc queries much more quickly,” comments Graeme Reed. “Furthermore, we plan to harness SAS Viya to automatically interpret and classify complaints, to enable our employees to focus on resolving issues rather than classifying them.”

Nationwide is also building a data lake, into which it plans to incorporate unstructured data. For example, Nationwide is keen to analyse voice data from calls to the contact centre, to build on their understanding of the enquiries arriving via this channel and look for more efficient and joined up ways to manage them.

Graeme Reed concludes: “It’s an exciting time to be working in analytics, as the field has become a major focus area within Nationwide. For example, we are consolidating our data and looking to harness more data sources, as well as improving our reporting and hiring new people. SAS continues to form a key pillar of our analytics landscape, and the SAS team helps us make the most of our existing solutions and recommends suitable products if we have new ideas. We enjoy working with SAS, and we are excited to see what we can achieve with them in future.”