Every call runs on a partial picture
Each system records transactions, so simple questions take a week of exports.
Enrollment
Recruiting agent
318 admitted students are behind pace
I drafted a campus visit invite for each one, from their counselor.
Approve and sendReview
Invites sent to 318 students
Why enrollment is hard to run today
Students wait weeks while their files sit in a queue
Applications, transcripts, and transfer credit are keyed and checked by hand.
A drop in applications can be a gain
Without the market backdrop, teams chase the wrong problem.
The enrollment model
We bring your systems, outside data, and policies together, model the domain, and compute what it runs on.
What the model enables
Forecast
The class, by segment
Census enrollment for each segment, with a range, updated daily.
Measurement
Share of every market
Your enrollments against each market’s college-goers, so a drop in applications reads correctly.
Prediction
Who will enroll
Each prospect’s chance of enrolling, and whether they are behind pace.
Optimization
The next best step
The touch most likely to move each prospect, learned from experiments.
Measurement
What actually worked
Lift from every tactic against a holdout, and the cost of each added deposit.
Rule
Transfer credit, evaluated
Prior courses matched to equivalencies, credits computed, exceptions routed.
What we deploy
Applications, agents, and workflows on the model. Each one reads the model and changes it only through governed actions.
App
An app where the enrollment team runs the cycle
The class forecast against goal by segment, every market’s share, prospects behind pace, and live experiments.
Reads from the model
- Entering class
- Segment
- Market
- Prospect
- Experiment
Agent
An agent that works the prospects behind pace
It sends the next best step within approved messages and logs every touch back to the model.
Reads from the model
- Prospect
- Milestone
- Touchpoint
- Campaign
Workflow
A workflow that processes applications, transcripts, and transfer credit
It matches prior courses to equivalencies and computes transfer credit. Exceptions go to an evaluator.
Reads from the model
- Application
- Transcript
- Prior course
- Course
What the enrollment model lets you do
How we measure
We report what a change should add, and what it actually added.
Projected value
What the model expects a change to add, set when it goes live.
Holdout
Students who don’t get the change, compared with those who do.
Matched group
Similar students from the same cycle, when a holdout isn’t possible.
Prior cycle
The same point last year, for changes that reach every student.
Start with Enrollment
We scope the first domain with your team and agree on the outcomes to measure.
How we deploy