How a logistics brand used call center analytics to raise agent satisfaction by 40%

In this case study, we unraveled the story of how one of the world’s largest logistics providers leveraged advanced analytics to improve its customer service department’s operations. Specifically, our client adopted the use of an AI-based text mining program to help them identify specific reasons behind an increasingly high volume of caller complaints.

The logistics company is headquartered in Europe and has offices in more than 150 countries.

It all began when our logistics client noticed more and more complaints reported by their call center operators, mainly from throughout Europe. The company did not know precisely why. Instead, it only knew a large volume of incoming data, which its entire organization could not always keep up with.

Also, at the time, our client had analysts whose skills were not advanced enough to analyze the data. Thus, further preventing executives from taking immediate actions. The company simply lacked the proper tools or technologies to help them uncover specific reasons behind employee and customer dissatisfaction.

As a result of their delayed decision-making, our client saw an uptick in agent turnover. This further led to more hiring of new replacements while increasing talent acquisition costs. The constant change in new agents affected the customers, who grew less and less tolerable every time they had to deal with a new support rep. New operators were not as knowledgeable about the client’s products and services as their senior peers.  Eventually, impatience led some customers to consider other delivery couriers.

Therefore, the logistics company needed to find a solution that could somehow help improve agent retention and customer satisfaction while also reducing the volume of call center support tickets.

Meet Anna, who has been working for our client for nearly 20 years as a Customer Care manager. She was mainly responsible for overseeing the Benelux region.  Over time, and like other senior executives in her firm, Anna realized the costs of maintaining a level of high-quality contact center operations were far exceeding the company’s own product sales.

Anna believed there had to be a more cost-effective solution to satisfy both employees and customers. That was when she learned about Wonderflow’s advanced analytics that could also cater to specific call center problems and needs. 

As a text mining software incorporating the latest artificial intelligence (AI) technology, the Wonderflow platform required no initial setup by Anna and her teams. While our clients shared as much as they could about their dilemma, we worked on configuring our AI to start automating the collection and analysis of data.

First, we needed to gather employee feedback. So, we devised an email survey for our client’s agents to understand their thoughts on the company and its workplace conditions. The questionnaires were shared in a few different languages to accommodate the agents’ preferences. Their recorded responses were received in a free-text format.

Next, Wonderflow collected the feedback to analyze, translate, and anonymize. Its advanced analytics power extracted insights from nearly 20,000 records in the entire call center database. Also, the data varied in a multitude of different languages.

The data came from both private and public channels and mainly from sources like emails, live chat conversations, and recorded phone conversations. The call logs were actually the most valuable source. By applying a speech-to-text analysis method, Wonderflow analyzed thousands of these phone transcripts between agents and customers.

Everything was performed in a single interface or platform. The results were then translated into a more visually appealing and understandable style for Anna’s team and other departments that may need the insights (e.g., marketing, R&D, design). At that point, the entire organization could better access and share the same customer information, thus reducing the risks of misinforming customers and employees alike.

Wonderflow enabled our client to quickly understand that many of their agents rarely reported critical customer concerns when they should be. The agents were mainly not sharing issues they knew they alone could not fix. Instead, operators were more or less fixated on only handling customers’ short-term needs. The most critical customer problems, which usually require more time to resolve, would either be left half-resolved or neglected entirely.

Our system detected several potential areas of call center process improvements. It could even alert our client’s managers with personalized suggestions on leveraging the call center data and discovering the impact of a decision’s outcomes.

Additionally, many call center operators had more free time on their hands to prioritize other more critical customer concerns, especially those with long-term requests and that have been postponed or neglected. By nurturing more of their existing and new customer relationships, the reps helped improve their customer retention rate.