By Bob Kasten
With the advent of computers, thoughts quickly turned to speculation that a computer could someday match human intelligence. In 1950 Alan Turing devised the Turing Test that became a threshold for when a machine is said to become intelligent. The test uses a human evaluator that watches a conversation between two parties. The evaluator knows that one of the parties is a machine, and if the evaluator cannot distinguish between the human and the machine, the machine is said to be intelligent.
While the notion of artificial intelligence (AI) can bring thoughts of computers someday becoming self-aware, we do not have to worry about this just yet. In our era, AI has become an important tool that can be used in contact centers to become a performance differentiator.
Machine learning is a branch of AI. It uses data to feed algorithms that automatically learn and improve. Machine learning falls into two broad categories: supervised and unsupervised. In supervised learning, the output datasets are provided and used to train the machine and get the desired outputs for future datasets. Unsupervised learning does not use output data, but instead the data is clustered into different classes and then analyzed.
Many industry verticals have become commoditized to the point where offerings are similar or the same across the competitive market. This applies to BPOs (business process outsourcers) as well as the companies that use their contact center services. In order to gain and keep market share, it is essential to give a best-in-class customer experience. Machine learning can help with this process.
Contact centers generate a multitude of data. Data sources include systems for CRM (customer relationship management), billing, collection, agent QA (quality assurance), call recording, chat, email, CSAT (customer satisfaction), social media, and so on. All this data tells a story about the customer and the contact center’s interaction with them.
The recent progress made in AI parallels similar progress with voice recognition and natural language-processing technology. It is now possible to convert real-time conversations or voice recordings to text with a high degree of accuracy. Having a conversation in a text format gives the ability to mine agent and customer interaction.
The easiest way to understand how data and machine learning can work together in concert is to describe a common scenario. The process uses an archetype that can be applied generally to supervised machine learning.
Here is a list of generic process steps, followed by a specific example that uses a voice recording as the data source. Note that the data could come from any of the above sources.
- Identify data source: Locate a voice recording.
- Generate learning data: Convert the voice into text.
- Machine learning analysis: Process text data.
- Machine learning correlation: Connect success and failure outcomes with patterns in the agent and customer conversation. Find out how the best agents generate success. Identify the criteria of the call that causes the interaction to be successful. The output of this step will produce actionable insights.
- Make improvement suggestions: Use the insights from the previous step to make enhancement recommendations. Improvements can come in many forms, including agent training as well as agent and customer matching. This provides real-time customer data the agent can use during future sales opportunities or script changes.
- Implement recommendations: Take action by improving the script or training the agent.
- Predict success: The insights gained from machine learning can be used to predict the likelihood of success. A benefit of predictability is that an action can be taken based on the predicted behavior.
- Feedback: Verify that agents are using the training recommendations by running the process iteratively to confirm that the feedback is contributing to attaining key success metrics. Feedback is also used in the success prediction.
Determine what successful agents say is the basis for building on that foundation and give it to agents who are not as successful. Once you know the why of success, you have taken the first step in answering how to improve it. Positive customer experience plays directly into understanding the success equation. A customer who makes a purchase or gives a positive customer satisfaction rating for the service they received will be identified by using the machine-learning process.
Other data sources can be added into the model to improve the predictability quotient. CSAT could be used to help further identify success patterns. Another possibility is using customer attributes that can be obtained commercially. Commercial data includes purchase habits, household income, age, gender, home market value, and occupation.
These data marts are a good way to give agents more direct information about customers. In addition, they are used to improve the accuracy of the predictive modeling. Customer attributes are used to enhance the customer experience and increase the likelihood of success. Many attributes about the customer that are found using their phone number or email address can give further insights.
Using a computer-generated call that speaks as if it were a human being brings this model full circle. This application has been deployed in the past couple of years. It still has a long way to go, because customers can tell the caller is a computer rather than a person. In 1950 Alan Turing probably never envisioned that his Turing Test would be used with automated dialing systems.
Using machine learning in conjunction with learning from the mined voice text, with the advances in natural language constructs, brings new opportunities, as seen with assembly-line automation in the early twentieth century. Calling and speaking using a computer reduces staff and leads to labor cost savings. It should be noted there are TCPA requirements, as well as state and federal laws, that should be thoroughly understood and followed before using this type of technology.
When we get to the point that a customer cannot tell that a machine called and is speaking to them, the Turing Test will pass, and the machine will be considered intelligent. Once that happens, we may be closer than we would like to the day when computational awareness becomes a reality.
Bob Kasten is the founder of contactcentertools.com. His tools provide a holistic suite of agent performance management modules that includes KPI performance tracking dashboards, voice analytics, QA scoring, knowledge testing, goals, coaching, and secure clean desk agent communication. He spends his time consulting on contact center information technology projects and enhancing his agent performance management tools. He can be reached at firstname.lastname@example.org or www.linkedin.com/in/bob-kasten/