Ordering
The right quantity in every store
Too much stock ties up cash, too little empties the shelf. sktime forecasts sales per product and store for the coming days, so your orders follow expected demand.
Use case · Retail
Less cash tied up in stock.Fewer empty shelves.
sktime is free, open-source AI software for demand forecasting. The sktime team sets it up on your sales data and supports you afterwards. You make better ordering decisions, even when demand fluctuates, without a data science team of your own.
Weekly sales · one product in one store
- Past sales
- Expected demand
- Your order
sktime shows the range demand is likely to fall in, so you can order enough without filling up the stockroom.
- Open source
- Free to use, and you can see exactly how it works. No license fees per user or product.
- Established methods
- Proven statistical and machine-learning forecasting methods, all usable through one consistent interface.
- Straight from the developers
- You work directly with the people who build sktime.
Where sktime helps in retail
Five places where better forecasts pay off.
Out-of-stocks and overstock cost retailers around 6.5% of their sales worldwide. That is where sktime comes in.(IHL Group, 2025)
Fresh food
Less waste on short shelf lives
Bread, produce, and dairy have to sell within a few days. Forecasts that take weekday and weather into account help you order only what will sell before it expires.
Promotions
Promotions without empty shelves or leftovers
A promotion pushes sales up for a week and often leaves stock behind. sktime includes prices and promotions in the forecast, so you can see how much extra stock a campaign needs and how demand develops afterwards.
Seasons
Ready for seasonal peaks
Christmas, Easter, and the first summer heat follow patterns that come back every year. sktime picks them up from your sales history, so you can build up stock in time.
Staffing
Enough staff when customers come
The same methods forecast footfall per store and hour. That gives your shift planning a reliable basis, with less idle time and shorter queues at the checkout.
What the numbers say
What modern forecasting delivers in retail.
Studies and practice reports show what forecasts based on machine learning achieve in retail. sktime brings these methods together in one open-source toolkit, so you can use them without building everything from scratch.
25%
fewer stock shortages in fresh produce
Reported on average by food retailers using AI-based planning systems, along with at least 10% fewer write-offs and up to 30% lower inventory planning costs.
McKinsey & Company, 201930%
fewer returns in bakeries
A machine-learning forecasting service cut bakery returns by 30% on average in 2022, mostly bread and rolls, according to sales reports.
Hübner et al., Journal of Industrial Ecology, 202420%
less surplus stock at Otto
Otto uses AI forecasts to steer part of its purchasing and reduced its surplus stock by a fifth.
The Economist, 2017sktime is open source: no license fees per user or product.
These figures come from studies and practice reports on machine-learning forecasting in retail, not from sktime projects. We work out what is realistic for your business in a first conversation, using your data.
How we start
Three steps to forecasts you can trust.
- 01
First conversation
We look at your data and where planning costs you the most today.
- 02
Pilot on your data
We build forecasts on a real slice of your sales data. You see the results before you commit to anything.
- 03
Use in daily planning
The forecasts go into your regular planning process. The developers behind sktime stay available when questions come up.
Before you ask
Questions retail executives often ask.
- We don't use any AI yet. Is it too early for us?
- No. Demand forecasting is a good first AI project because you can measure the result directly in stock levels and sales. A pilot on a slice of your data shows the effect before you commit to anything. We agree its scope and timeline with you in the first conversation.
- Is our data good enough?
- Usually, yes. Sales history per product and store from your ERP or checkout system is enough to start. Prices, promotions, and holidays improve the forecast and can be added later.
- Do we need to hire new people?
- No. The sktime team, made up of the developers who build sktime, sets up the forecasts on your data and stays your contact afterwards. The forecasts then run automatically for every product and store, so your planners spend less time in spreadsheets and never have to write code.
- Does our data stay with us, and will it work with our systems?
- sktime runs on your own servers or in your own cloud, so your data doesn't have to leave the company. It works with the sales data your ERP or checkout system already exports, and the forecasts go back into your ordering process as files or through an interface. Because sktime is open source and developed by a broad community, you can check what it does at any time and are not tied to a single vendor.
- What does it cost?
- sktime itself is free, with no license fees per user or product, now or later. You only pay for the setup and support you want from the sktime team. Once we have seen your data in a first conversation, we can estimate that effort.
For your planning team
What is behind the forecasts.
Your planning team will want to know how the forecasts are made. Here is the short version.
Code example for your technical team- Ranges instead of a single number (probabilistic forecasts)
- Every forecast comes with a range and probabilities. Your team sets safety stock to match the risk it is willing to take.
- One model for many products (global models)
- sktime learns from related products and stores together. New and slow-selling items benefit from that too.
- Real-world drivers (exogenous variables)
- Holidays, promotions, prices, weather, and store data can all feed into the forecast.
- Figures that add up (hierarchical reconciliation)
- Forecasts for products, stores, and regions add up at every level. Purchasing, stores, and management plan with the same numbers.
Open source meets enterprise
Find out what better forecasts can do for your business.
sktime is free and open source. If you'd like to use it on your own sales data, the team behind sktime can help you get started.