Introducing NPS Insights: How Machine Learning helps you find the signal in the noise
“How likely are you to recommend us to a friend or colleague?”
It’s a simple question. Yet, Net Promoter Score (or NPS) has become the industry standard for measuring customer satisfaction. NPS is a powerful tool. It gives you a quantitative score to measure how you stack up—but the true gold mine lives in the qualitative responses users submit along with their numerical score. These open text responses help product teams understand the “why” behind the number and hold valuable insight into your product’s strengths and weaknesses.
Unfortunately, when it comes to qualitative data, it is possible to have “too much of a good thing.”
The problem is, the more NPS data you collect, the harder it is to act on it. Without context, NPS quickly just becomes a number with no “why.” And when you’re contending with a mountain of qualitative data, real insights can feel out of reach. To actually be able to extract value, you need to identify common themes in all those qualitative responses.
Historically, product or support teams have had to resort to manually digging through each NPS response in search of common threads. But all this manual data processing wastes time that could be better spent helping customers, building advocates, and creating a data-driven roadmap.
Product and support teams need tools to extract insights, so they can focus on impact.
Introducing machine learning for NPS
Now, product teams can transform qualitative NPS data from a time waster into a differentiator with NPS Insights, powered by Pendo Simon. NPS Insights leverages machine learning to identify key themes in open-text NPS responses, so you can easily see the common threads among your promoters and detractors.
By getting machine learning algorithms to do the dirty work of manual data analysis, you can unlock new levels of efficiency and insight for your team. With NPS Insights, teams can…
Drill into key themes
Surface the most common feedback amongst promoters or detractors. With automatic theme detection, teams can use the time they would’ve spent organizing and surfacing takeaways to actually act on the data. Use themes to present to leadership, prioritize your product roadmap, and build the things your customers actually want.
Track how themes are trending over time
Track how key themes are trending over time to see if subsequent product improvements make an impact on customer sentiment, or if any product areas become more urgent pain points.
Create segments from themes
Group users based on feedback, and use those segments to identify common product behaviors or to target follow-ups and announcements as you make improvements.
You can use NPS Insights segments to…
- Identify a common usage pattern between the detractors that referenced your product’s user experience as a problem
- Conduct deeper research on how you could make your onboarding experience better
- Recruit advocates and champions who think your product is easy to use to add to your pool of social proof
With machine learning for NPS qualitative data, everyone wins: Product and success teams spend less time sorting and coding data, and leadership teams get immediate access to actionable insights. With NPS Insights, teams can find the signal in the noise, go from insight to impact, and focus on the work they actually want to do: acting on key insights to make users’ lives better.