HackerTrans
TopNewTrendsCommentsPastAskShowJobs

crimeacs

no profile record

Submissions

Show HN: Funnel – Find a convesion leak on any landing page in 30 seconds

funnel.fyi
5 points·by crimeacs·mese scorso·2 comments

148,421 posts later: A model to predict the Hacker News front page

hackernews.foresyn.ai
15 points·by crimeacs·2 mesi fa·3 comments

comments

crimeacs
·mese scorso·discuss
Thanks, paul_knoxops! We will work on that
crimeacs
·2 mesi fa·discuss
Author here - quick context so this doesn’t read like a hot take.

Dataset: 148,421 public HN stories from Algolia since 2007, filtered to score ≥5. Split is strictly chronological: train < Jul 2025, val Aug–Dec 2025, holdout Jan 2026+. Random splits are misleading here because kNN features leak future neighbors.

Model: LightGBM with 4 heads: median, p10, p90, and score ≥100 classifier with isotonic calibration. Compiled to plain JS via m2cgen and runs inside a Vercel function — no Python/ONNX/runtime. ~10 MB bundle, sub-ms inference.

Holdout:

* Spearman ρ = 0.33 on log_score

* MAE log = 1.65, roughly ~5x off in raw points

* AUC for score ≥100 = 0.67

* Precision@30 = 0.83

So: not magic. About one-third of the signal seems recoverable from title/context. AUC is below ontology2’s 2014 title-only baseline, around/above recent BERT fine-tunes I found.

Two things I haven’t seen elsewhere:

1. Comment simulator grounds every fake comment in a real top comment from a kNN neighbor, with `[src]`. 2. `/predictions` runs a live calibration ledger against actual HN top 30 every 10 min, so the model can’t hide behind a static benchmark.

Open source, MIT, training scripts included: https://github.com/crimeacs/foresyn-hackernews

I ran the submitted title through the model first. It predicted 32/99 virality and ~12 points. The ledger will soon tell us whether it was calibrated.

Roast away.