Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. Capacity Planning for a Seasonal Business
AI & Machine Learning

Capacity Planning for a Seasonal Business

Sizing for peak wastes money for months; sizing for average fails when it matters. How to structure the decision and what to forecast.

Updated 2 min readBy SpiderHunts Technologies

Free estimateNo obligation

Get a free estimate

Tell us what you need. A senior engineer reads every enquiry.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →

Quick answer — TL;DR

The useful output is not a demand forecast but a decision about which capacity is fixed and which is flexible. Forecast the peak with an honest range, then decide how much of it to meet with permanent capacity.

The structural problem

A business whose demand triples in season faces a choice with no comfortable answer. Permanent capacity sized for peak idles for months; sized for the average it fails customers exactly when demand is highest.

Forecasting helps, but the decision is about capacity structure rather than about the forecast. A perfect forecast still leaves the question of what to do about it.

Split capacity by how it flexes

TypeExamplesLead time to change
FixedPremises, owned equipment, core staffMonths to years
Semi-flexibleSeasonal contracts, leased equipmentWeeks to months
FlexibleAgency, overtime, subcontractDays
Demand-sideLead times, booking windows, pricingImmediate

The bottom row is the one most often forgotten. Managing demand - extending lead times in peak, incentivising off-peak booking, staging deliveries - is capacity management, and it is usually the cheapest lever available.

Forecast the peak, with a range

For a seasonal business the annual total matters far less than the peak. Two years with identical totals can be entirely different operationally if one has a sharper peak.

  1. Forecast at the granularity the constraint bites - daily or weekly, not monthly, if that is where capacity fails.
  2. Produce a range rather than a point, since the plan needs to cope with the bad case.
  3. Forecast peak timing as well as height; a peak arriving two weeks early causes different problems.
  4. Model the shoulder periods, where the ramp up and down are frequently where the real cost sits.

Peak timing deserves attention. Recruitment and training have lead times, and being ready two weeks late is nearly as bad as not being ready.

Cost the shortfall honestly

The decision needs a number for what happens when capacity is exceeded. That is rarely just a lost sale.

Depending on the business it may be a lost customer permanently, a penalty clause, overtime at premium rates, expedited freight, or reputational damage in a peak-season review cycle. Those costs are what justify carrying capacity that idles.

Write them down before the planning conversation. Without them the argument reduces to risk appetite and whoever is most persuasive.

Build in review points

A seasonal plan set in advance and not revisited will be wrong. Building in decision points - by this date, given bookings so far, we commit to the additional capacity or we do not - converts one large uncertain decision into several smaller informed ones.

Each review uses the booking curve to date, which is far more informative than the pre-season forecast. Designing those checkpoints is usually worth more than improving the original forecast.

The forecast is not the decision. The decision is how much capacity you are willing to leave idle in February.

FAQ

Frequently asked questions

The questions readers ask us after this guide.

Still have a question?

Ask us directly — a senior engineer will get back to you.

Ask about your project

How much history for a seasonal forecast?

At least three years to distinguish the seasonal pattern from year-specific events, and more if seasons vary a lot.

What if last year was unusual?

Flag it explicitly rather than letting the model average it in. A disrupted year can distort a seasonal profile for years afterwards.

Should we forecast in hours or units?

In whatever unit your constraint is measured in. If the constraint is skilled labour hours, forecast that, not revenue.

Is flexible capacity always more expensive per unit?

Usually, which is the trade. The comparison is unit cost against the cost of idle fixed capacity plus the cost of shortfall.

Keep reading

More on AI & Machine Learning

Start here

Want machine learning project details from us?

Tell us what you are trying to predict and roughly what data you hold. We will come back with an honest view on whether machine learning is the right tool, what the work would involve and a realistic cost range. If a spreadsheet would do the job, we will say so.

  1. You tell us what you needTwo minutes on the form, or a message on WhatsApp.
  2. A senior engineer reviews itAnd comes back with questions, a realistic range and an honest view on fit.
  3. Free 30-minute scoping callWe talk through scope, options and a realistic estimate — with no obligation.
Free estimateNo obligation

Talk to someone who builds this

Send a short brief and we will come back with an honest view and a realistic range.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →