“The software has to automatically recognize early on that the customer may soon get angry.”
E.ON is a leading energy provider that faced significant difficulties and challenges in managing its call center operations. E.ON's previous system relied on manual or rule-based sorting of the calls, and with over 50 000 calls monthly, it resulted in inefficiencies and errors. The lack of an automated call categorization system led to ineffective call analytics, and therefore advanced analytics like churn prediction or customer sentiment was impossible to detect.
To address these challenges, E.ON partnered with SentiSquare, a provider of a powerful natural language processing tool. SentiSquare AI designed to handle natural language processing and sentiment analysis helped E.ON to address its challenges comprehensively.
Automated Call Categorization: SentiSquare implemented a system that helped E.ON to classify and categorize the calls by topic automatically. By analyzing the transcription of the calls, the system could accurately sort the calls into relevant categories efficiently and without needing to read the text or listen to the calls.
Customer Sentiment Detection: SentiSquare AI solution provides sentiment analysis algorithms that detect the sentiment of the conversations between the customer and employee and helps to identify dissatisfied and satisfied customers. This can help E.ON to turn dissatisfied customers into satisfied customers.
Customer Journey Recognition and Churn prediction: Using the SentiSquare AI solution, E.ON could analyze multiple customer calls over time and map the customer's journey and churn prediction.
The deployment of SentiSquare AI solution resulted in significant benefits for E.ON:
Efficient call categorization: Call agents could now focus on the satisfaction of the customers and addressing the customer's concerns instead of manual call sorting.
Reduced Churn, Increased Loyalty: By implementing SentiSquare AI solution, the call agents can detect dissatisfied customers and react proactively. This can prevent churn prediction, increase loyalty and improve brand reputation.
Improved customer experience: E.ON can now understand the customer journey and identify the crucial areas for improvement.
Higher prediction accuracy: Regular learning and adaptation of the system further increases the prediction accuracy and enhances the effectiveness of the call analytics system.
“Customer care has an important role in FTMO. Often these are recurring queries, where SentiSquare text analytics helps to speed up responses to our clients and save routine work for agents. This allows them to focus on more complex queries.”
“SentiSquare’s contextual email processing saves our employees work. Our Front Office operators now spend less time on routine tasks, instead focusing more on client care.”