CPHML An applied AI and Machine Learning Company

Target the
people who will
actually say yes

We score every contact in your next campaign with a personalized ML model, so your outreach budget only goes towards the audience most likely to respond. Same revenue, at a fraction of the cost.

RANKED LEADS · OUTPUT n = 148,200
# ACCOUNT tx interval segment score contact
01 d_8841 12d a7 0.94 1
02 d_3019 31d a4 0.88 1
03 d_9903 18d b3 0.81 1
04 d_2287 44d a9 0.74 1
05 d_5612 62d b1 0.68 1
t = 0.62 · cut-off
Threshold T is chosen to maximize expected ROI.
Expected return at T = 0.62
kr 2.4m
Projected return
contact12,400 skip135,800
Who it's for

Teams running high-volume
outreach where every contact
has a cost

If your sales, fundraising, or retention teams contact thousands of leads by phone, mail, email, or ads, not every contact is worth the same effort. We help you score who is most likely to convert before the campaign starts, so your team can focus budget and attention where it has the highest expected return.

Direct sales teams

Use cases
  • Call center campaigns
  • Outbound sales calls
  • Win-back campaigns
  • Cross-sell and upsell

Fundraising

Use cases
  • Direct mail
  • Telemarketing
  • Email campaigns
  • Donor reactivation

Retention & subscriptions

Use cases
  • Renewal campaigns
  • Churn prevention
  • Trial conversion
  • Retention offers

Customer growth

Use cases
  • Loyalty campaigns
  • Repeat purchase prediction
  • Dormant customer win-back
  • Targeted offers
How it works

1 DATA
contact_id recency freq payment channel d_8841 12 6 1.240 call d_3019 240 1 200 post d_9903 31 14 3.400 email d_2287 410 2 450 post

We prepare your data

We combine and transform your existing customer or donor data - purchase history, engagement signals, demographics, and campaign activity - into a tailored dataset designed for prediction and targeting.

Zero engineering on your side
2 MODEL

We predict response

A machine learning model trained on the curated dataset outputs a ranked list of contacts based on their predicted likelihood of donating, purchasing, or converting. Alongside the predictions, we provide a full feature importance report giving complete visibility into the behavioral patterns most strongly associated with lead conversion.

Conversion prediction · behavioral insights
3 TARGETING
τ

Target the top-scored contacts

Using the ranked predictions, we determine the optimal targeting threshold for your campaign. The result is more efficient outreach, lower campaign volume, and stronger operational performance.

Efficient targeting · Measurable impact
Recent work

Ongoing · 2026

Optimising donor campaigns for Danish Red Cross

By scoring their donor base before each Direct mail and Telemarketing campaign, we identify which contacts are unlikely to donate in a given cycle. Substantially increasing campaign yield by reducing print, postage and sales agent costs. Reducing physical material waste also helps our customer reach its sustainability goals.

Danish Red Cross
National humanitarian org · est. 1876
InputDonor data
ProcessPredict Donor response
OutcomeWorst leads discarded
Increased ROI
Get started

Ready to focus on the contacts most likely to convert?

Send us your campaign setup and we'll propose a fit within 3 business days.

Get in touch