"You can have data without information, but you can't have information without data" - Daniel Keys Moran
Today, only 2%-5% of all call center calls are QA'ed, for no reasons other than, humans are expensive and manual scoring is time consuming. Well, now there is a scalable way to QA 100% of your calls.
Looking for more info on Auto Call Scoring?
- Auto Call Classification by VoiceBase
- How To Transition From Human Scoring To Auto Call Scoring in 5 Easy Steps
- 3 Major Benefits Of Auto Call Scoring For Cloud Contact Centers
What is Auto Call Scoring?
Auto call scoring is the process by which machine learning algorithms train using results previously defined by humans (such as hot lead, rude agent, upset customer, etc). This training process allows these machine learning platforms to zero-in on the key variables that define each pattern, in order to determine the result of all future calls.
Why does it matter?
As much as they would like to, call centers cannot afford to humanly score 100% of their recorded calls. Right now they are doing the "next best thing", humanly scoring as many calls as financially makes sense, unfortunately that only amounts to 2%-5% on average. Every call center that fits that description is losing valuable data every day by not listening to the other 95%-98% of their calls. Call Centers are missing a customer's thoughts on a competitor, they're missing an opportunity to up-sell a product that a similar customer bought, and they're missing pre-churn signs that would allow them to prevent account cancellations. Never miss data again.
What can you detect?
1. Script Adherence
There are certain terms agents should be saying on every call, '5 year guarantee, 'zero-down', '30 day free trial', '6 month commitment', etc. Now you can use calls where the agent hit the necessary points, and calls where the agent missed important information as training data to spot the absence of these phrases, to know which agents need extra training or which calls need to be reviewed.
2. Profanity/NSFW Behavior
Swear words are not uncommon in a call center, a lot of callers are upset on the phone lines, so spotting every swear word would probably be moot. But you should know if your agents are the ones with foul mouths, right? If you record in stereo (or channel/multi-party, whatever you want to call it), you can search just agent side recordings or set flags to alert supervisors if the agent side detects any NSFW terms or phrases.
3. Competitor Names
Wouldn't you love to be a fly on the wall when your customers are talking about your competitors? Now you can! Customers are quite candid on the phone, they mention competitor prices, marketing campaigns and other factors that effect the buying process. Spot competitor names and see what your customers really think.
4. Positive/Negative Comments
Ever perform agent reviews? Imagine having a list of all of the negative and positive comments a customer has said when on the phone with this agent. By using calls that have been tagged with specific time stamps during a "positive" comment and a "negative" comment, it is unbelievable how accurately the machine can pick up those little nuances that define each. Now agent reviews are a cinch!
5. Redact Sensitive Information
Lastly, some call centers can't even record their calls because of the information being spoken; there are credit card numbers, social security numbers and mother's maiden names being exchanged. With machine learning, companies can simply check a box in the API to redact PCI, SSN or PII to produce a queryable database of content.