Capacity and Staffing Forecast
Four to six weeks, from $14,500, fixed. We forecast how many patients each unit will have and test the forecast on your own history against the method you use now. If it does better, we send it each day where your staffing office already looks, such as a morning email or the dashboard it uses. It runs on hourly counts, with no patient records.
Prefer to skip the call? Get a written proposal
Built for
- Community hospitals without a capacity command center
- Staffing offices that plan from the same week last year
- Emergency departments forecasting arrivals
- Clinics and medical groups forecasting visits per day at each location
Why it's worth it
Today
Next week's staffing is set from the same week last year and a manager's experience. When more patients come than planned, overtime and agency staff fill the gap, and when fewer come, paid hours sit idle.
After
Each morning your staffing office sees how many patients each unit is expected to have, with a low and a high estimate in beds. Before anyone relies on it, a test on two years of your own history shows whether it beats the method you use now.
What you get
Week 1
The staffing decision
Who sets staffing, how far ahead, and how many beds of error they can live with.
Weeks 2–4
Model and backtest
We build the forecast from two or more years of hourly census by unit, plus scheduled surgery counts. The backtest then runs it on past months it never saw and reports how many beds it was off by. For a clinic, the same steps forecast visits per day at each location.
Weeks 4–6
Go or no-go
The forecast compared with the method your staffing office uses today. If it doesn't beat that method, we'll say so plainly and the work stops there.
After a go
Production forecast
A daily forecast sent where staffing decisions are made, such as a morning email or the dashboard your staffing office already opens, with a check that flags when accuracy slips.
What it builds on
The forecast draws on Tyler's experience with time-series analysis, the machine-learning and statistical models he has built for Medicare cost and quality research, and the queueing math (how arrivals, waits and full units affect each other) behind the Throughput Diagnostic.
Two steps, priced separately
You pay for the backtest first, and the production forecast is quoted only if the backtest beats your current method. If the forecast passes the backtest and you build it, the whole project comes to $42,500 to $54,500.
Backtest
Step one, for every forecast
Price: $14,500
One time
4–6 weeks
A census forecast built on your own history and tested against your current method, ending in a go or no-go.
What's included in Backtest
- Who sets staffing, how far ahead and how much error they can accept, written down
- A forecast for each unit from two or more years of hourly counts
- Error measured in beds on months the model never saw
- A side-by-side with your current method and a plain go or no-go
Production forecast
Step two, only after a go
Price: from$28,000
Up to $40,000, quoted after the backtest.
One time
Set after the backtest
A daily forecast for each unit, sent where staffing decisions are made, with a check that flags when accuracy slips.
What's included in Production forecast
- A daily forecast for each unit, with a range in beds
- Delivery where your staffing office already looks
- A check that flags when accuracy slips
- The code and documentation, handed to your team
- 30 days of fixes; support after that is optional at $500 to $1,500 a month, on the same terms as our data and analytics services
Payment and terms
- Under $20,000, half at signing and half at delivery. From $20,000, 40% at signing, 30% at a mid-build demo and 30% at acceptance
- Paying by purchase order? There's no deposit: we invoice half at kickoff and half at acceptance, or from $20,000, 25% at kickoff, 35% at a mid-build demo and 40% at acceptance
- Hourly counts only: no patient records
- The production build is priced only after a go, and the backtest is paid for on its own
Start and finish dates are set in writing in your proposal.
Tyler Kent does this work himself. He has 13+ years in data science and analytics, most of it in healthcare. About Tyler
Questions
What data do you need?
Hourly census counts by unit for at least two years, plus scheduled surgery counts if surgery drives your census. Counts only.
Why a backtest first?
A forecast is only worth using if it beats what your staffing office does today. The backtest measures that on your own history before the larger build is priced.
What if the backtest says no-go?
Then the work stops at $14,500 and you keep the backtest. It shows, in beds, how accurate your current method is.
How is this different from a capacity software platform?
It is a forecast built on your own counts and handed to your team, priced once, with no platform subscription.
How is this different from the Throughput Diagnostic?
The forecast tells your staffing office how many patients to plan for. The Throughput Diagnostic finds the step that holds patients up and what to change there.
Does it work for clinics?
Yes. The same method forecasts visit volume for a clinic or medical group.
How an engagement worksQuestions about prices, payment and patient data
Book a 20-minute call
Tell us how your staffing office plans the week ahead. If we can help, you'll get a fixed-price proposal within 48 hours.
Prefer to skip the call? Get a written proposal
Or email tyler@kentapplied.com, or connect on LinkedIn.