Page 21 - AeM_May_2020
P. 21
RESEARCH
ANALYSIS
TRENDS
Most well-known AI models for language are designed Here’s how conversational AI works in Invoca’s call
for either long, carefully edited texts like news articles, tracking platform:
or for short, spontaneous speech like a Tweet or
chatbot conversation. In our experience, none of these Step 1: Call data flows into the Invoca platform during
well-known models work on phone calls, which are both each conversation.
long and spontaneous. Since analyzing phone calls
differs so starkly from the rest of the research Step 2: The spoken data is transcribed into text so it
community, we did our own research and develop our can be analyzed by the algorithm.
conversational AI algorithms. Invoca’s conversational
analytics platform is designed to help marketers get a Step 3: The predictive model analyzes the conversation
new view into conversation data from high-intent and identifies key patterns, phrases, and actions, then
consumers — such as purchases made or promotion identifies call outcomes such as ‘application submitted’
inquiries. Marketers can quickly gain new insights and or ‘quote received’.
get attribution from phone calls and take action on them
in real time. It is used to drive more revenue-generating Step 4: Those outcomes and insights are pushed into
calls, boost conversion rates, and optimize the buying your marketing stack so you can use this valuable
experience. Signal AI conversational analytics is most conversation data to optimize marketing spend and
frequently used to: personalize the customer’s next interaction — all in real
time.
• Optimize ad spend: automatically adjust keyword The latest addition to the Signal AI conversational
bidding strategies and suppress ads in systems like analytics suite is Signal Discovery. Powered by
Google Ads and Search Ads 360 for callers who unsupervised machine learning, Signal Discovery gives
convert over the phone you an unprecedented view of phone conversations
with your customers by automatically grouping
• Seed audiences: create new audiences using customer conversations into topics based on
offline conversion data to expand your reach of similarities in speech patterns. This allows marketers to
potential customers through native integrations with quickly gain new insights from tens of thousands of
Facebook and Adobe Experience Cloud conversations and acting on them. There is no better
way to get to know someone than having a
• Personalize content: update content management conversation, and there is no better way to get to know
tools like Adobe Target to personalize content for your customers than by making conversational
each subsequent consumer visit based on call analytics part of your marketing tech stack. Feel free to
conversations download Invoca’s State of First-Party Marketing Data
report. ◊
Compared to other conversational analytics tools,
Signal AI offers marketers deeper insight into the
unique conversations happening between a By Owen Ray,
businesses’ buyers and agents — often uncovering Senior Content Marketing Manager ,
conversation patterns and behaviors that marketers Invoca
didn’t know existed — with consumer-level data that
can be made actionable across marketing platforms.
21 May 2020: Natural language processing & conversational analytics: data quality beyond