Our own product2026HisseAnaliz
A stock decision-support tool that states its own uncertainty in numbers.
- Project
- Our own product
- Our role
- Product · Data engineering · Machine learning
- Duration
- 3 months
01 / Behind the product
A real need. A considered solution.
Challenge
Most tools that produce buy or sell signals never say how sure they are. A confident-looking signal is harmful when it cannot be told apart from chance.
Approach
A rule-based decision carries entry, stop and target levels, with a meta-labelling model as a filter on top. The important part is the statistical honesty layer: hit rate and p-value sit next to every call.
Result
A tool that runs locally. Not investment advice, but a second opinion for questioning your own call.
02 / Inside the product
The experience, on screen.
Open a screen to explore the details.02 images
03 / Scope & details
The details make the experience.
- 01
Rule-based calls with entry, stop and target levels
- 02
A filter trained with meta-labelling
- 03
Hit rate and p-value beside every call
- 04
Runs locally, no data leaves the machine
Technology
Python / FastAPI / LightGBM / Anthropic Claude
Your idea could be next.
What could we build for you?
From a first release to a growing platform. Let’s plan the design, development and launch together.
From Türkiye to the US, UK, Australia and everywhere in between.