This website uses cookies to technically implement the functions of our site. With your consent, we also use third-party services to improve the functionality of our website as well as for performance analysis and targeting/advertising purposes, which help us to improve our website. By clicking on "Accept all cookies" you declare your consent, which can be revoked at any time. Further information, in particular on the storage period and recipients, can also be found in our data protection notice & cookie policy.

30 November 2021

Improving PayPal's NPS with Conversational analytics

We’ve been partnering with PayPal for 14 years now. Their ambition is to provide the best customer service and the safest interactions. We’ve been able to overachieve and reach their dream NPS target of 60+.

 

PayPal trusts us to take care of their most important relationships - the ones they have with their customers. We do that by providing customer care in digital and voice channels in French, Italian, Arabic, and English, in the French, Italian, Middle East & Africa, and Canadian markets.

 

By investing in operational improvements and digital solutions we managed to achieve 62.88 NPS and reduce RCR by -8.52%.

 

One of the key drivers of these improvements was the Center of excellence we built for them. This way we were able to discover areas for improvement and suggest multiple solutions, one of which was implementing a conversational analytics tool in order to improve NPS.

 

By using conversational analytics, we’re able to monitor 100% of recorded calls and written conversations to analyze the customer and agent sentiment. What is Sentiment? As it applies to customer service and contact centers, sentiment is generally referred to as a method of measuring emotion in customer and agent interactions. The reason behind this measurement is to analyze interactions to uncover areas of improvement.

 

Using sentiment to score agent interactions removes the need for random sampling because the interactions are already scored. It also empowers quality programs to analyze 100% of interactions to get a true sense of trends and the reasons behind them. The sentiment model takes into consideration: 

 

  • Language used by customers and agents can indicate a positive or negative sentiment
  • Laughter detection can indicate a positive change in an otherwise negative conversation 
  • Cross-talk (where the agent and customer talk over each other) might indicate confusion or frustration
  • Changes in pitch and tone or speaking rate can signal changing satisfaction during the interaction

 

Conversations with negative sentiments most often result in lower NPS. So we decided to do callbacks to each customer that exhibited negative sentiments in conversations with our agents. High-performing and senior agents would call these customers within 24h after the initial interaction and talk to them about the issue they had, in an attempt to increase their satisfaction with the support we provide. 

 

During the last quarter of 2021 and the first quarter of 2022, we were able to increase NPS by +6.85 pts thanks to 11.586 callbacks made by the sentiment task force (composed of 4 extra mentors fully dedicated to this task) with a 70% success rate, and we indirectly helped in reducing almost 1% in Recontact rate.

 

Being the client’s Center of excellence for this tool worldwide, we’re able to create queries that can be validated and improved to ensure the accuracy of data. The team will grow by 4 more people starting from July 2022 as this year we’ll be working on 300 new queries.

 

Check out more of our digital solutions.

Read the whole story about how we reached PayPal's dream NPS score of 60+.