This section describes the feature that surfaces the three attributes most strongly associated with above- or below-average win rates at any given pipeline stage.
1. Overview
“Conversion probability drivers” are characteristics of an opportunity (industry, age in funnel, activity counts, etc.) that, historically, have increased or decreased its likelihood of closing. Each driver is shown as a percentage relative to the average win rate for all deals at that stage:
A +30 % adjustment means deals with this characteristic closed 30 % more often than average.
A –40 % adjustment means deals with this characteristic closed 40 % less often than average.
2. Data Sources & Scope
Historical Wins
Only deals marked Closed-Won within the past 1–5 years are used to identify success patterns.All Opportunities
Every deal in your CRM (regardless of outcome) is used to measure baseline frequency of each characteristic.
3. Measured Variables
Default Variables (captured at the selected starting stage)
Stage Duration: Time spent in the stage
Age in Funnel: Time since opportunity creation
Activity Counts: Total logged interactions (emails, calls)
Activity Diversity: Number of different activity types
Campaign & Channel Touches: Counts by source (e.g. email, events, ads)
Additional Attributes
Industry (e.g. Financial Services)
Lead Source (e.g. Web, Events)
Opportunity Type (e.g. New vs. Renewal)
Company Size (e.g. Revenue band, Employee band)
…plus any other custom fields you configure.
4. Calculation Methodology
For every factor (e.g. Industry = “Technology”) and each of its values (e.g. “Technology”, “Healthcare”):
Likelihood
Likelihood=Count of Closed-Won Opps with Feature=Value / Total Closed-Won Opps
Marginal
Marginal=Count of All Opps with Feature=Value / Total Opportunities
Adjustment
Adjustment=Likelihood/Marginal
Positive Adjustment (> 0 %) ⇒ over-performance
Negative Adjustment (< 0 %) ⇒ under-performance
Example:
• 20 % of Closed-Won deals are in “Financial Services” (Likelihood)
• 15 % of all deals are in “Financial Services” (Marginal)Adjustment = (0.20 / 0.15) – 1 = +0.33 ⇒ +33 % adjustment
5. How It Appears In-App
Top 3 Drivers
The three factors with the largest positive or negative adjustments are listed, in descending order of absolute impact.Adjustment Value
Shown as a “+ X %” or “– Y %” badge next to each factor name.
Factor | Adjustment |
|---|---|
Financial Services (Industry) | + 33 % |
Age > 90 days (Funnel Age) | – 12 % |
Calls > 5 (Activity Count) | + 28 % |
6. Best Practices & Caveats
Sample Size: Very small cohorts (e.g. < 10 deals) may produce volatile adjustments—treat them as directional only.
Time Window: You can tailor the historical window (1–5 years) to reflect market shifts.
Cross-Filtering: Remember that factors are analyzed independently; two positive drivers may not stack linearly.
Custom Fields: If you add new opportunity fields, re-index your historical data to surface new drivers.
By understanding which attributes most strongly correlate with wins, you can focus efforts on opportunities that look “primed” for success, and take corrective action on those that show risk factors.