Skip to content
English
Contact us
  • There are no suggestions because the search field is empty.

Driver Analysis

Understand which topics have the greatest influence on KPIs like NPS, satisfaction, or star ratings, and where to focus for the biggest impact

Key driver analysis is a powerful way of measuring the relative impact of topics on a KPI. Below is a detailed explanation of how Caplena combines open-ended text categorization with ratings and performance measures to deliver these insights.

This feature helps you understand how much a topic influences performance metrics, such as:

  • Likelihood to recommend (e.g., NPS)

  • Overall satisfaction

  • Star ratings

  • And other custom KPIs

What’s Included in the Driver Analysis?

The driver analysis includes four key elements:

drivers

Chart Section Details
Impact per row Measures impact on the performance metric on an individual basis. Based on multiple regression analysis.
Net impact Shows overall impact by combining strength and frequency of mentions.
Suggestions for improvement AI-powered recommendations on how to improve key topics.
Driver Impact vs. Mentions Scatter plot showing driver strength vs. frequency for easy prioritization.
 

Impact per Row

Topic sentiment plays a key role in the driver analysis, allowing us to determine the impact of a topic based on positive and negative experiences.

  • The color coding of the bars reflects sentiment-based impact.

  • The numbers next to the bars show regression coefficients.

  • The higher (or lower) the number, the stronger the impact on the likelihood to recommend.

The impact or driver strength can vary significantly by topic.

Examples:

  • NETWORK QUALITY / Reliability
    The red and green bars are nearly equal in length, meaning both positive and negative experiences significantly influence the likelihood to recommend.

→ Someone mentioning unreliable network quality would likely not recommend the provider.

  • DEALS & PRICING / Price
    A negative price perception has a very strong negative impact.
    A positive perception does not significantly boost recommendation.

→ This indicates a “hygiene driver” (Kano model): customers expect good pricing and react strongly when it’s perceived as poor.

 

Net Impact

The impact per row is an interpretation on a case-by-case basis. Any given topic might be a very strong driver with a very high impact on a customer’s likelihood to recommend, but to measure the overall impact on a KPI over the total sample, we need to consider the frequency with which that topic was mentioned.

How Net Impact Is Calculated

For the net impact calculation, we combine:

  • The driver strength

  • With the frequency of a topic mentioned

This allows us to determine to what extent the NPS (in our example) is influenced overall.

NPS is not a simple linear metric - it’s based on a non-linear step function. For example, if someone’s score increases from 2 to 6, they are still considered a detractor, and the overall NPS remains unchanged. To address the limitations and randomness introduced by this rigid structure, we use advanced probabilistic modeling to estimate the true net impact more accurately.

Case-Specific Interpretation

The impact shown for each row reflects a case-specific interpretation. While a particular topic might strongly influence an individual customer’s likelihood to recommend, it is also crucial to consider how frequently that topic was mentioned across the entire sample to understand its overall influence on the KPI.

Example:

Taking BRAND PERCEPTION / Overall perception as an example:

  • This topic has the highest net impact based on the combination of driver strength and frequency.

  • Although that topic has a significant negative impact when raised by an individual, it is most often associated with positive experiences—resulting in a strong overall net contribution.

 Additional notes:

  • The topic is mentioned often (n = 191, see Mentions in the screenshot)

  • Some topics may be mentioned more frequently

  • However, driver strength and number of positive or negative mentions ultimately determine the net impact


The net impact shows the current contribution to a score or rating.

In the case of the NPS example above:
BRAND PERCEPTION / Overall perception = +9.1 points
DEALS & PRICING / Price = -3.8 points

This reflects how topics positively or negatively contribute to the overall KPI score.

 

Note:

The driver chart currently supports NPS and 5-Star Rating as dependent variables. Additional performance metrics will be added soon.

 

Suggestions for Improvement

For each topic, Caplena provides AI-generated suggestions based on:

  • Open text analysis

  • Driver calculation results

In the example above, the suggestions touch on NETWORK QUALITY / Connectivity & coverage, but also intelligently bring in related areas such as pricing when appropriate.

 

Driver Impact vs. Mentions

CleanShot 2025-07-21 at 21.04.16@2x

Clicking the icon in the top-left of the suggestion box toggles a scatter plot that visualizes:

  • Horizontal axis → Impact

    • Right = Positive impact

    • Left = Negative impact

  • Vertical axis → Mention frequency

This allows you to identify priority areas quickly.

 

 

🎥 Need a Walkthrough?

Check out the video guide below for a step-by-step explanation of how to use Driver Analysis in Caplena.

undefined