For most product and service companies, a major portion of their maintenance expenses is spent on customer support. Leadership at these organizations understandably seeks to reduce this cost without compromising quality.
Moving forward, machine learning will assume a major role in addressing customer support challenges. The technology can automate the process of identifying problems and recommending fixes, with or without human intervention, which speeds problem resolution, improves customer satisfaction and reduces costs. Moreover, machine learning-based solutions can create a continuously evolving expert system for agents, based on historical and current troubleshooting data.
Traditional vs. Machine Learning-Driven Customer Care
In a typical customer care center, the workflow begins when a customer calls a support agent, who collects symptoms of the problem, makes a diagnosis, collects more clues and then consults a knowledge base or troubleshooting guide for possible solutions. This is generally an iterative process, involving multiple steps until the problem is resolved.
Throughout the process, troubleshooting data is recorded in a log that contains information about the customer interaction. Generally, this content is neither structured nor straightforward, making it difficult to summarize without human assistance. Thus:
Troubleshooting data is represented in a chatty question-and-answer info dump.
The troubleshooting workflow differs for each product/service, based on the issue observed and line of business.
The overall volume of troubleshooting data is typically very high.
With machine learning, systems use pattern recognition and algorithms to learn from and make predictions on data. Today, practical machine learning solutions have transcended high concept to become near-term reality across multiple disciplines and industries.
In customer care, machine learning gathers the knowledge of hundreds of agents and subject matter experts and makes it accessible to support agents. By enabling expert knowledge of the troubleshooting log, and improving the ability and skill of support agents, machine learning solutions can ultimately reduce customer resolution times.
We recently introduced a machine learning-based system, code-named ASIMOV that uses software and processes to address common customer problems and overcome troubleshooting challenges. With this system, customer support centers can extract insights from complex troubleshooting data; correlate various symptoms, problems, actions, fixes and resolutions in the troubleshooting log; and automatically recommend fixes and solutions to quickly resolve customer problems.
ASIMOV works by creating a mathematically-based predictive machine learning model using the data gathered and analyzed by subject matter experts. Using a large volume of historical troubleshooting logs, the system generates a more generalized machine learning model for predicting problem resolutions and recommendations to customer issues.
For example, when a support agent feeds the system with a clue or looks up a current customer problem, ASIMOV quickly predicts and recommends the best solutions, based on what it has learned from previous customer challenges and related fixes. This way, agents can access a solution that has proved effective for other agents, and can navigate the recommended path to quickly resolve the issue.
Making It Happen
To address a variety of customer care challenges for call center optimization, ASIMOV’s machine learning solutions support big data ecosystems and cloud-based environments. The system also provides accelerators to bring machine-learning-based solutions more quickly to market. We have successfully piloted ASIMOV for a communication services provider, which has helped the company optimize customer complaint troubleshooting.
With its deep understanding of customer care problems and customized machine learning support software, ASIMOV can efficiently address critical business goals that challenge customer support centers, including making more intelligent decisions, reducing time spent on customer support calls, recommending troubleshooting approaches and solutions, reducing dependency on human agents, and automating predictive solutions.
To learn more, please read “Optimizing Customer Support with Machine Intelligence,” or visit our Intelligent Process Automation Practice. To get ahead with AI, please read our new book from the Cognizant Center for the Future of Work, “What To Do When Machines Do Everything,” Feb. 2017, John Wiley & Sons.