July 27, 2018 Marketing Analytics

A recent survey of 300 B2B marketers, performed by EverString and Heinz Marketing, found that less than one-fifth of respondents truly understand the difference between artificial intelligence, machine learning, and predictive modeling.

If this confusion is keeping marketers from adopting AI, it’s unfortunate. AI is  such a powerful asset to marketers—it’s helping brands and agencies analyze marketing data with unprecedented precision, providing them with the insights to make smarter optimizations that drive more revenue at lower costs.

What Is AI vs. Machine Learning?

Below we’ve provided a quick refresher, for those of you who need it.

AI: Short for artificial intelligence, AI is a machine’s capacity to imitate intelligent human behavior.

Machine Learning: A subset of AI, machine learning is a machine’s ability to process data and make adjustments to its behavior based on that data in order to eventually reach a desired outcome.

We’ve written about how brands are using AI to personalize the customer journey and acquire more customers. But here at DialogTech, we are all about voice analytics, and we have solutions that use both machine learning and AI to uncover insights from conversations at scale.

Using Machine Learning to Categorize Inbound Calls

Your marketing generates a lot of calls, but are they all sales leads? How do you know what marketing sources generate the most sales leads vs. support calls? How does your marketing team know what products or services each caller is calling about from each channel (for example, home insurance vs. auto insurance vs. motorcycle insurance)? Knowing the answers can help you make smarter marketing optimizations. You can have machine learning analyze conversations and do the categorization for you.

For example, at DialogTech marketers can categorize a sample of inbound calls to your business and build custom machine-learning algorithms that will take it from there, automatically detecting patterns they can use to categorize calls for you moving forward. Our data science team can provide you with support as needed.

What’s a Good Example of How Marketers Can Use Machine Learning to Analyze Calls?

One of the world’s largest luxury automakers uses search marketing to drive conversions and customers to their network of 350 dealerships in the US. Because a luxury vehicle is a considered purchase, many consumers call their local dealer before visiting, making calls an important conversion for the automaker’s marketing team. They are not only tracking the tens of thousands of monthly calls they generate from paid and organic search to their dealerships, they are using machine-learning algorithms to analyze what’s said on those calls to categorize each caller as:

A Sales Call: Caller that asks for the sales department, asks about new or pre-owned vehicles, schedules a test drive, asks about leasing information, and more.

A Service Call: Caller that asks for the service department, sets a maintenance appointment, mentions a recall, asks about oil changes, mentions an issue with their car, and more.

A Parts Call: Caller that asks for the parts department or enquires about tires, keys, or a specific part.

Other: Caller that needs roadside assistance, tries to solicit business, doesn’t leave a voicemail message, is spam, hangs up before someone answers, and more.

By using DialogTech and machine learning to understand the types of calls the automaker drives from paid and organic search, when those calls come in, and what devices callers engage with their ads and websites, the marketing team can optimize messaging, targeting, and bid strategies to drive more of the calls that drive revenue.

Using AI to Analyze Phone Conversations at Scale

For marketers in many industries, including insurance, health care, automotive, travel, home services, and more, phone calls are one of the most common conversion paths for customers. Therefore, in order to optimize their campaigns (targeting, messaging, spend), marketers should extract and analyze what their customers are saying on this channel. However, with many brands generating tens of thousands of call recordings or more a month, trying to derive marketing insights seems insurmountable.

That’s where artificial intelligence comes in: AI can analyze these vast sets of conversation data and provide marketers with actionable insights. Not only is AI faster at detecting patterns than humans, but it’s also more accurate—machines are not prone to fatigue, human error, or other biases. Therefore, using AI to locate trends from your phone conversations will provide you with a strong competitive edge.

How Do AI-Powered Conversation Analytics Work?

Step 1: Call data flows directly into the DialogTech platform.

Step 2: Artificial intelligence automatically “listens” to every call and transcribes the conversations into highly accurate text between the caller and the agent.

Step 3: Our algorithms listen for dozens of proprietary sales call indicators within each transcription, including key phrases, patterns, and the business outcome (such as “appointment set” or “purchase made”). Using these indicators, we provide you with metrics like lead score, sales opportunity, and conversion rate.

Step 4: The resultant insights are published in your intuitive DialogTech dashboard, allowing you to see a holistic picture of the impact calls are having on your marketing, sales, and service departments.

Step 5: You can also integrate these insights directly into your martech stack. DialogTech offers integrations with major platforms, including Google AdWords, Bing, Facebook, Salesforce, LiveRamp, and many more.

What Insights Can I Gain from Using AI-Powered Conversation Analytics?

Let’s say you’re a marketer at a national home services franchise with hundreds of frachisee locations. Prior to using call analytics, you were allocating most of your marketing spend to paid search ads, since they were driving the most calls to your franchisees. However, upon integrating AI voice analytics you realize that, although Facebook ads are driving less total calls, these calls have nearly double the lead score of your paid search ads. So, instead of optimizing your marketing campaigns for call quantity, you optimize for call quality, resulting in higher revenue.

AI can automatically score leads and sort by marketing source.[Sample Report] Track which marketing sources are generating the highest quality leads.

Continuing with the example, let’s say your average lead score for these Facebook ads is 7 out of 10. However, you notice that a significant number of these leads aren’t converting. You can drill down and view the conversion rate by franchisee location, allowing you to understand how calls are being handled. You may notice that a particular location is underperforming—you can then dig deeper and search the transcriptions to understand why. Are your franchisees using the right scripts on calls? Are they mentioning the right offers or even asking the caller for appointments? Based on your findings, you can provide additional coaching to improve the conversion rate of phone calls.

Marketers use AI to segment call KPIs by location

[Sample Report] View sales conversion rates by franchisee location and monitor how many calls are sent to voicemail.

Finally, you can use the AI-generated data to assist with customer retention. AI-powered conversation analytics can automatically detect when customers are likely to churn. Using this information, you can alert franchisee locations when issues surface during phone calls and have their owner/manager take action, perhaps calling the lead back to provide a personal touch or a special offer.

Marketers use AI to learn which customers are at-risk in real-time

[Sample Report] View a real-time list of frustrated or at-risk customers, curated by AI.

Through this holistic view of the call channel, companies can ensure their marketers are driving high-quality leads, their sales staff is closing them at a high rate, and their customer service department is retaining these customers.

If you’d like to learn more about how businesses are using AI to convert callers to customers, check out our Digital Marketer’s Playbook for Voice Analytics.

To learn more about how AI can help you make smarter optimizations and boost your conversion rates, check out our Digital Marketer’s Playbook for Voice Analytics.

Get the Guide →
About the author:

Alain Stephan

Senior Vice President, Analytics Services, DialogTech

As DialogTech's SVP of Analytics Services, Alain loves data. He is passionate about telling a story with data and helping marketing and sales leaders harness the power of the voice channel. He has deep experience in analytics, with the last decade dedicated to turning call data into meaningful insights for business transformation. Alain is a proud alumnus of both Miami University and the University of Chicago Booth School of Business. He resides in Chicago’s northern suburbs with his wife and three kids.

See more posts by Alain Stephan

Enjoying our content?

Get the latest straight to your inbox.