HN Explorer

madman2890

↗ HN profile [ 79.9 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Relational signal compression across your data lake (kurve.ai)
    1 points 0
  2. Why Most Valuable AI Systems Are Still Tabular Models

    The Hard Part of Predictive AI Isn’t the Model I’ve spent most of my career building predictive systems on tabular data. The highest-value AI systems I’ve seen in production aren’t LLMs. They’re predictive models that…

    6 points 1
  3. Predictive AI with graphs and tabular foundation models (wesmadrigal.github.io)
    2 points 0
  4. Tabular data is the frontier – graphs can help

    Even in 2026, most of the work in tabular predictive AI still has very little to do with the model itself. Whether you're using CatBoost, XGBoost, or newer tabular foundation models like TabPFN, the .fit() step is…

    5 points 1
  5. Tabular Foundation Models Still Need One Thing: Multi-Table Aggregation (wesmadrigal.github.io)
    2 points 1
  6. 1 points 0
  7. 1 points 1
  8. Library for feature engineering across many table using graphs (wesmadrigal.github.io)
    1 points 0
  9. 1 points 1
  10. 1 points 0
  11. 1 points 1
  12. 1 points 1
  13. 1 points 1
  14. Feature Engineering Abstractions with Graphs (github.com)
    2 points 0
  15. 1 points 1
  16. 1 points 1
  17. 1 points 1
  18. 1 points 0
  19. Show HN: built a feature engineering interface based on graphs (github.com)
    1 points 1
  20. Who is funding the border crisis?

    According to the CBP website there were 144,278 border apprehensions/inadmissables in May of 2019. In May of 2018 there were only 51,862. That's an increase of 278% year over year. Is there any data behind an…

    2 points 3
  21. Datanectar – project to mitigate friction between data science and engineering (github.com)
    5 points 2
  22. Write it yourself (wesmadrigal.blogspot.com.co)
    1 points 0
  23. Legacy Database Integration in Django (wesmadrigal.blogspot.com)

    I was having some issues integrating django with some legacy databases at work and came up with this solution.

    1 points 0