Services · AI and data
Machine learning, forecasts and optimisation
I build models that forecast demand, prices and risk from your own historical data. Every forecast shows what it relies on and how certain it is.
ResultA forecast with a confidence range and an explanation of where it comes from.
Who it is for
- Stock, prices or schedules are set by gut feeling.
- There is plenty of data, but no decisions are made from it.
- You need to estimate which customer will buy, leave or is risky.
- Allocating resources (people, vehicles, storage) takes a lot of manual time.
What I can do
- Demand and sales forecasts
- Price recommendations and comparables
- Sale, churn and risk probability
- Optimisation: schedules, routes, resources
- An explanation of what the model relies on
- The model as an API or dashboard in your system
Input → output
| Input | Output |
|---|---|
| Two years of sales history by product group | A demand forecast for the next 8 weeks with a range |
| Details of a new product or listing | A suggested price, sale probability and similar examples |
| Orders, addresses and staff availability | A proposal for who does what, and in which order |
A typical format, not a client project. There is no public optimisation example yet.
Proof
- Founder’s independent projectMarketplace Intelligence
Six models in one workspace: price recommendation, sale probability and demand forecast based on 1.47M listings and 5M behavioural events. Open the demo
- Founder’s independent projectGlobal Risk Forecast
A LightGBM model estimates regional risk from historical data and shows it on an interactive map. Open the demo
How the work goes
- Understand the task. A free conversation about your workflow, programs and what gets in the way.
- Agree the proposal. I agree the outcome, scope, price and timeline in writing before starting.
- Build the solution. I show you interim versions and gather your feedback so the solution fits your workflow.
- Test with your data. Together with you I try typical work scenarios and fix any issues found before rollout.
- Hand over the system. You receive the solution, guide and access. I show you how to use it; ongoing support is agreed separately.
Price
- One automationfrom 490 €
- Projectfrom 2,000 €
- Maintenance and supportfrom 120 €/ per month
The first conversation is free. The exact figure depends on the number of sources, document types and special cases – you get it in writing before work starts. All prices →
Questions
How much data is needed?
It depends on the task. A forecast usually needs at least a year of history. As a first step I review your data and tell you honestly whether a model will help.
How do we know the model works?
We test it on data the model did not see during training and compare it with a simple baseline (e.g. the same period last year). I show the results as numbers.
Do you do optimisation problems?
Yes: schedules, routes, resource allocation. There is no public example of this yet, so we start with a small trial on your data.
Let’s discuss your task
Write a few sentences about what is still done by hand. I reply personally.