Applications of data mining and machine learning in online customer care

Abstract

With the coming of age of web as a mainstream customer service channel, B2C companies have invested substantial resources in enhancing their web presence. Today customers can interact with a company through channels such as phone, chat, email, social media or web self-service. With the availability of web logs, CRM data and text transcripts these online channels are rich with data and they track several aspects of customer behavior and intent. 24/7 Customer Innovation Labs has developed a series of data mining and statistics driven solutions to improve customer experience in each of these online channels. This talk will focus on solutions to enhance performance of web chat as a customer service channel. 2 stages of customer life-cycle will be considered -- new customer acquisition (or sales) and service of existing customers. In customer acquisition the key objective is to maximize incremental revenues via chat. While in customer service the objective is to drive up the quality of customer experience (measured by customer satisfaction surveys or mined customer sentiments) through chat. The solution based on machine learning methods involves: Real-time targeting of the right visitors to chatPredicting customer needsRouting customer to the right customer service agentMining chat transcripts and Social Media Portals to identify key customer issues and customer sentimentsMining agents' responses for performance improvementFeeding back learning from 4 and 5 to 1 (better targeting)Real-life case studies will be presented to show how that this closed loop solution can quickly improve key metrics.