▶ Demand and sales forecasting
Your inventory problem is not always an inventory problem.
I build a demand forecast on your own sales data and put inventory, purchasing and production planning on a measurable basis instead of experience alone.
There is no perfect forecast. There is one that knows its error and plans around it.
Atalay Deveci · Updated 2026-10-08
What this service actually is
Demand forecasting uses past sales, seasons, promotions and other effects to predict how much will sell in the coming period. The value is not in the forecast itself but in how it connects to planning: how much stock to hold, when to order, how to plan production.
It is not a crystal ball and it doesn't replace the planning team. It makes the forecast the team builds by hand every month systematic, measurable and repeatable, so the team can spend its time on the exceptions.
The uncomfortable part
Overstock and stockouts are usually blamed on a bad forecast. Most of the time the problem sits around the forecast.
Past sales are not past demand.
A product that is out of stock can't be sold. Sales during stockouts understate demand, and a forecast built on that data carries the same gap into the next period.
There is a forecast, but it isn't tied to the plan.
If the forecast lives in one file and the purchasing decision is made in another meeting, there is no link between them. The right stock level can't be found without considering the forecast error and safety stock together.
Every product is forecast the same way.
Fast, steady sellers and slow, irregular ones shouldn't be forecast with the same method. One approach for everything works for one group and produces errors in the other.
I will tell you early which of these applies. If I see your data isn't enough for a forecast, I will tell you that too.
▶ How I work
- Week 1
Data and the current process.
Sales, stock and promotion data are reviewed together with today's planning process. The accuracy of the current forecasting method is measured, giving a baseline to compare against.
- Weeks 2–3
Model and product groups.
Products are grouped by sales behaviour and a fitting method is chosen for each group. Forecasts are compared with the current method over the same period.
- Weeks 4–5
Connecting to planning.
The forecast, together with its error, is turned into stock and order suggestions, in the format the planning team uses, refreshed on a schedule.
- Final week
Handover.
How the model works, when it needs updating and how to monitor results is documented and handed to your team.
▶ When you should not hire me for this
If any of these is true for you, let's not start this engagement:
You don't have enough history.
For a new product range or a new company, a statistical forecast won't be reliable. The data needs to build up first.
Your sales depend on a few large contracts.
When demand hinges on a handful of customers' decisions, working closely with sales beats a model.
The forecast won't change anyone's decision.
If purchasing and production decisions will be made regardless of the forecast, this work is only a cost.
The real problem is on the supply side.
If supplier lead times are unpredictable, even the best demand forecast won't solve the stock problem on its own.
▶ Engagement shape
If your data is ready we start with a fixed-scope pilot of 4–6 weeks on one product group or channel. If the data situation is unclear, a ~2-week AI & Data Opportunity Assessment first makes clear what is possible.
The scope is agreed in writing up front. At the end of the pilot, the forecast's performance against your current method has been measured.
- 30-day exit
- If it isn't working, you can end the engagement with 30 days' notice.
- Invoiced from Türkiye
- I invoice through my company registered in Türkiye.
- Reply within 24 hours
- I reply to every message within 24 hours.
▶ Questions and answers
How much history is needed?
It depends on the product and seasonality. A seasonal business needs data covering at least a few seasons. In week one we make clear whether what you have is enough.
How accurate will the forecast be?
It wouldn't be honest to say before starting. In the pilot, forecasts are compared with your current method over the same period, so the result comes to you measured.
Are promotions and holidays taken into account?
Yes. Promotion calendars, holidays and similar effects are included in the model when they are in the data.
Does it work with our existing ERP?
The forecast is produced in the format the planning team uses. How it flows into the ERP depends on your existing setup.
▶ Fastest route
Start with one email.
The link below opens an email with the questions that make the first conversation useful already written in. No form, no account. I reply within 24 hours.
hi@klarvoanalytics.com
▶ Other services
- Corporate trainingsThe team can't work with data.
- In-house AI assistantsCompany knowledge gets lost in documents.
- Customer analyticsLost customers are noticed too late.
- Reporting and data infrastructureReports are built by hand and take days.
- Custom dashboardsOff-the-shelf BI tools can't show what we need.
- Fractional data science leadNobody owns data.