Egor Kraev
where else to find them
linkedin:egorkraev
what they talk about
all 4 in the filters
where they keep going back
- PyData London2 editions2017–2019
on a stage with
never shared a talk
who talks about the same things
- Aleksander Molak6 talks
- Kalyan Prasad9 talks
- Vincent D Warmerdam22 talks
- Anna Warno5 talks
- Maurits Kaptein3 talks
- Benjamin Bengfort6 talks
| title | conference | date |
|---|---|---|
| Dr. Egor Kraev | AI Track | Compass AI & Data Summit 2025 | Compass AI & Data Summit 2025 | 2025-11-12 |
Claims a reliable pattern for getting LLMs to emit complex, validated objects rather than free text, using Pydantic objects as the schema, a validator-as-tool… | ||
| Modelling and predicting customer lifetime value | Crunch Conference 2021 | 2021-10-07 |
Compares classic Buy Till You Die models implemented with the lifetimes Python package against a custom variational autoencoder + RNN that ingests event… | ||
| Choose the right neural generative model for your problem | PyData London 2019 | 2019-07-12 |
Advice hinges on concrete tradeoffs: pick models by output structure and whether an objective exists. Continuous outputs favor direct nets or autoencoders for… | ||
| Easy Bayesian regularization for fitting financial time series and curves | PyData London 2017 | 2017-05-05 |
Claim: massively overparameterize curves and then remove degrees of freedom with convex regularizers and you get robust fits. Uses Python notebooks (code on… | ||
| nothing matches | ||