Customer Interaction Analytics
Enghouse Interactive has partnered with ContactBabel to bring you the 2012 ContactBabel Decision Makers’ Guide. The following is an excerpt from the Guide discussing Customer Interaction Analytics.
The term Customer Interaction Analytics refers to the analysis of all interactions between contact centers and customers, whether that interaction was via telephone, email, a web chat session, or even social media. Such conversations are “free-form” by their nature, hence any data captured from the interaction will be unstructured by definition, which makes this data more difficult to analyze. However, there is an enormous amount of valuable information hidden in this mountain of unstructured data, and analytics technology has evolved to the point that the customer interaction analytics technology available today is very effective at capturing the voice of the customer and improving contact center performance based upon information gleaned from interactions.
The evolution of analytics
In the late 1990s, data warehousing was a big growth industry, especially in sectors such as retail, where the widespread usage of customer loyalty cards gave huge amounts of data about customers, their buying patterns and preferences. However, getting the data into storage was not the difficult part: the greatest value came from being able to identify and analyze the relevant and insightful patterns within these data, through data mining. In many cases, the reality never lived up to the hype, as the analytical capabilities of data mining tools and
businesses’ ability to use them effectively did not match the ease with which the data warehouse was filled in the first place.
Customer interaction analytics solutions are analogous with the data warehousing and mining applications in as far as they analyze huge quantities of data – here, unstructured data such as call recordings or emails, etc. – and identify important and insightful patterns in customer and agent activity. Hence, speech analytics is also called audio mining (it should be noted that some speech analytics solutions act in real-time, so the analogy is not quite exact), and text analytics is also called text mining. However, unlike the gap in functionality between data
warehousing and data mining that we saw a decade ago, customer interaction analytics solutions offer a proven and insightful option to release the customer value that is stored in these enormous quantities of information: insight about the customer, the agent, the business processes and the products and services that the business sells.
Within the contact center industry, speech analytics is probably the best understood and most used aspect of customer interaction analytics. The first speech analytics product for commercial purposes was released in 2002 (before then, the technology was used primarily for government intelligence purposes). Since 2002 the technology has improved considerably, as have the number of successful customer implementations.
The elements of speech analytics
There are various elements to speech analytics solutions, including:
- Speech engine: a software program that recognizes speech and converts it into data (usually either phonemes
- the sounds that go to make up words – or as a text transcription, although there are solutions which directly recognize entire spoken phrases and categorize calls with higher accuracy based upon the occurrence of those phrases, as no data is lost in conversion ).
- Indexing layer: a software layer that improves and indexes the output from the speech engine (when the speech engine is phonetic or speech-to-text) in order to make it searchable
- Query and search user interface: the desktop application where users interact with the speech analytics software, defining their requirements and carrying out searches on the indexed data
- Reporting applications: the presentation layer of speech analytics, often in graphical format
- Business applications: provided by vendors, these pre-defined modules help improve agent coaching and/or quality monitoring with speech analytics data, or look at specific issues such as adherence to script, debt collections etc, and provide suggestions on what to look for.
Speech analytics solutions are in use in 24% of our respondents’ operations, with the services, outsourcing and finance respondents more likely to be using it. There is an appreciable amount of interest in implementing within the near future, with 14% overall stating that this is likely, a figure which is particularly high in the medical and insurance sectors.