Service · Prague & remote

Machine learning and data for business decisions

Prediction, classification, computer vision and data analysis with TensorFlow, Keras and PyTorch, for businesses in Prague and across the EU. My bachelor's thesis at CTU predicted urban heat maps from satellite images with convolutional neural networks, and at ECOTEN I built machine-learning models for thermal data prediction.

Tools I use
01

What you get

Prediction and forecasting

Models that forecast demand, prices, risk or failures from your historical data.

Computer vision and OCR

Recognising objects, defects or text in images, scans and video.

Data pipelines and dashboards

Clean, automated data flows and dashboards that people actually use.

Proof of concept first

A small, measurable experiment on your data before any larger investment.

Deployment to production

Models wrapped in APIs, monitored and retrained — not left in a notebook.

Clear explanations

Results explained in business terms, including where the model is unsure.

02

Related projects

Real projects from my portfolio that this service builds on.

03

How we work together

  1. 01

    Free consultation

    A 30-minute call or meeting about your goals, customers and budget.

  2. 02

    Proposal & fixed quote

    A clear scope, timeline and price — before any work starts.

  3. 03

    Design & prototype

    You see and click through the solution early and shape it with feedback.

  4. 04

    Development & testing

    Built in short iterations with regular previews, tested on real devices.

  5. 05

    Launch & support

    Deployment, monitoring and help after launch — plus maintenance if you want it.

04

Frequently asked questions

How much data do we need?

It depends on the task. Some problems work with a few thousand records, others need more — or can start from a pre-trained model. A proof of concept tells us quickly.

Machine learning or generative AI?

Classic machine learning is best for predicting numbers and categories from your data; generative AI for text, documents and conversation. Many projects combine both.

Can the model run on our own servers?

Yes. Models can be deployed in your cloud, on your own servers or on devices, depending on data and latency requirements.

06

Let's talk about your project.

Tell me what you need — a free 30-minute consultation, no obligation. I reply personally.