Trial-to-Paid Conversion
“Which free trial users will upgrade to a paid plan in the next 14 days?”
Book a demo and get a free trial of the full platform: data science agent, fine-tune capabilities, and forward-deployed engineer support.
By submitting, you accept the Terms and Privacy Policy.
Loved by data scientists, ML engineers & CXOs at
A real-world example
Which free trial users will upgrade to a paid plan in the next 14 days?
SaaS companies with free trials convert only 5-15% of trial users to paid plans. Product and growth teams lack visibility into which trial users are likely to convert, leading to generic onboarding sequences that fail to activate high-potential users. Meanwhile, power users who would convert with a timely nudge churn silently at the end of their trial. The difference between a 10% and 15% trial conversion rate can mean tens of millions in ARR.
How KumoRFM solves this
Relational intelligence for smarter acquisition
Kumo connects USERS, FEATURE_USAGE, and SUBSCRIPTIONS into a relational graph that captures the full onboarding journey. The GNN learns conversion patterns across feature adoption sequences — like 'free users who used the collaboration feature 5+ times and invited a teammate within the first 3 days convert at 8x the base rate.' The WHERE clause filters to active free-tier users, and the model predicts conversion probability with 14-day lookahead, giving growth teams time to intervene with targeted offers or onboarding nudges.
From data to predictions
See the full pipeline in action
Connect your tables, write a PQL query, and get predictions with built-in explainability — all in minutes, not months.
Your data
The relational tables Kumo learns from
USERS
| user_id | plan_type | signup_date | company_size |
|---|---|---|---|
| U201 | free | 2025-10-20 | 50 |
| U202 | free | 2025-10-22 | 200 |
| U203 | free | 2025-10-25 | 15 |
| U204 | free | 2025-10-28 | 500 |
FEATURE_USAGE
| usage_id | user_id | feature | count | timestamp |
|---|---|---|---|---|
| FU01 | U201 | dashboard | 12 | 2025-10-21 |
| FU02 | U201 | collaboration | 8 | 2025-10-23 |
| FU03 | U201 | export | 3 | 2025-10-25 |
| FU04 | U202 | dashboard | 2 | 2025-10-23 |
| FU05 | U203 | dashboard | 18 | 2025-10-26 |
| FU06 | U203 | api_access | 6 | 2025-10-28 |
| FU07 | U204 | dashboard | 1 | 2025-10-29 |
SUBSCRIPTIONS
| sub_id | user_id | plan_type | amount | timestamp |
|---|---|---|---|---|
| S01 | U201 | pro | $99/mo | 2025-11-03 |
| S02 | U203 | team | $249/mo | 2025-11-08 |
Write your PQL query
Describe what to predict in 2–3 lines — Kumo handles the rest
PREDICT COUNT(SUBSCRIPTIONS.* WHERE SUBSCRIPTIONS.PLAN_TYPE != 'free', 0, 14, days) > 0 FOR EACH USERS.USER_ID WHERE USERS.PLAN_TYPE = 'free'
Prediction output
Every entity gets a score, updated continuously
| USER_ID | TIMESTAMP | TARGET_PRED | True_PROB |
|---|---|---|---|
| U201 | 2025-10-20 | True | 0.88 |
| U202 | 2025-10-22 | False | 0.14 |
| U203 | 2025-10-25 | True | 0.82 |
| U204 | 2025-10-28 | False | 0.06 |
Understand why
Every prediction includes feature attributions — no black boxes
User U201 — free plan, company size 50
Predicted: True (88% probability)
Top contributing features
Used collaboration feature 8 times in first 3 days
8 uses
30% attribution
Used export feature (premium activation signal)
3 uses
25% attribution
12 dashboard sessions (high engagement)
12 sessions
20% attribution
Company size 50 (team plan sweet spot)
50 employees
16% attribution
Similar users at same company size converted 6x more
6x base rate
9% attribution
Feature attributions are computed automatically for every prediction. No separate tooling required. Learn more about Kumo explainability
PQL Documentation
Learn the Predictive Query Language — SQL-like syntax for defining any prediction task in 2–3 lines.
Python SDK
Integrate Kumo predictions into your pipelines. Train, evaluate, and deploy models programmatically.
Explainability Docs
Understand feature attributions, model evaluation metrics, and how to build trust with stakeholders.
Bottom line: Targeted intervention for trial users predicted to convert lifts trial-to-paid rates by 45%, while identifying at-risk high-potential users early enough to save them — translating to millions in incremental ARR for product-led growth companies.
Related use cases
Explore more acquisition use cases
Topics covered
One Platform. One Model. Predict Instantly.
KumoRFM
Relational Foundation Model
Turn structured relational data into predictions in seconds. KumoRFM delivers zero-shot predictions that rival months of traditional data science. No training, feature engineering, or infrastructure required. Just connect your data and start predicting.
For critical use cases, fine-tune KumoRFM on your data using the Kumo platform and Data Science Agent for 30%+ higher accuracy than traditional models.
Book a demo and get a free trial of the full platform: data science agent, fine-tune capabilities, and forward-deployed engineer support.
