What is CSATai?
Tethr’s CSATai is designed to predict a customer satisfaction score for every customer interaction, eliminating the need for surveys. With Tethr’s CSATai, you can gain a holistic view of the customer service experience–and glean insights to improve your service delivery. By identifying factors that are decreasing customer satisfaction and actions that can be taken to improve it, businesses can maximize customer loyalty, reduce churn, improve future sales, and enhance their reputations in the market.
Early Adopters help Tethr:
- Validate and improve scoring accuracy
- Understand how the data is being applied to your organization
- Shape the product experience
How it works
To maintain and improve customer satisfaction, it is necessary to both identify the level of satisfaction and to identify what factors influence satisfaction. Customer satisfaction surveys are generally used to accomplish this but because surveys are voluntary, the sample is not truly random and can introduce bias.
Tethr’s CSATai uses machine learning models to measure satisfaction at the level of the individual customer interaction. The models were trained on millions of CSAT surveys and their preceding interactions (phone calls or live chat), allowing them to capture the mathematical relationships between survey scores and the words or phrases used in the interactions.
The models were then fine-tuned to ensure equal accuracy for good and bad survey responses, eliminating some of the affirmation bias present in the survey data. Next, the model parameters were tested against untrained data to ensure they could generate CSAT predictions for new interactions with a high degree of accuracy.
How to provide feedback:
- Open CSATai reporting
- Under section Providing Feedback, Open reports labeled “To Review"
- Open and review individual interactions and their CSAT label
- After each review, ask yourself "If I were the customer on this interaction, would I be satisfied or dissatisfied?"
- Based on this answer, you'll apply the appropriate public label
- Apply the appropriate public label
- CSAT Agree
- CSAT Switch to Dissatisfied
- CSAT Switch to Neutral
- CSAT Switch to Satisfied
It's important to review an equal amount of interactions from each CSATai range, Tethr's recommendation on total # of interactions to review is 20-25 per week per reviewer.
The more feedback provided by customers will directly result in the improvement of CSATai.