Warwick Analytics has launched an app for Zendesk users that applies automated classification and tagging for support tickets.
Through the app Warwick Analytics will apply its Machine Learning-based interaction analytics to unstructured customer data within support tickets whether they come via chat, web forms or email.
The full topics, sentiment and emotional intents of the contact will be automatically analysed and classified, accurately in near real time. This saves the call center or helpdesk having to classify each ticket manually, or using keyword classification which can be inaccurate.
Users will be able to set alerts for the early warnings of issues and complaints so they can be triaged, and where necessary prioritised and escalated fast. This means that an issue that could otherwise become a brand-affecting event, such as a serious customer issue that might otherwise end up on social media, can be dealt with by the right person at the right time.
The PrediCX app also features Multi-label Capability which means it can identify and classify multiple topics, sentiments and intents within a single piece of customer feedback, something that is often missed with human or generic ML classification.
Dan Somers, CEO at Warwick Analytics adds: “With the new app Zendesk users can analyse customer interactions across all customer touch-points, and use the insight to define and optimise support strategies. Helpdesks will be able to improve the speed of resolution, provide more relevant responses and streamline their chat optimisation process.”
Lee Mostari, Director of Insights & Analytics at Ember, a partner of Warwick Analytics, adds: “The world is becoming faster-moving with consumers demanding quicker service and more transparency than ever before. This Zendesk App enables brands to deal with the right queries in the right order and optimise the customer experience. Not only does this optimise customer operations, but it helps to protect and maintain the brand as well to enhance customer advocates and minimise customer detraction which from digital customers can both quickly amplify on social media.”