eriklindernoren/ML-From-Scratch — GitHub trend

FINDING #2201 · UNIT ID 80990461

eriklindernoren/ML-From-Scratch

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00013

ENGAGEMENT0.45

FRESHNESS1.01

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

1.66

ACCEL

-0.03

RETENTION

0.9%

PEAK 2026-05-31 · FORK-RETENTION 6.4% · 298 STARS / WINDOW

Author Audience

AUDIENCE

12,734

FOLLOWERS

5,944

OWNER ★

67,897

Engagement Signals

FORKS

5,422

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 296 / 298 (DIVERSITY 0.99)

Why This Is A Finding

eriklindernoren/ML-From-Scratch собрал 298 звёзд за окно, тогда как у автора всего 5,944 подписчиков — эффективная аудитория ≈ 12,734. Это даёт surprise-индекс 0.00013 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 6.4% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 14% OF 2559 FINDINGS

#02databricks-solutions/ai-dev-kit[ PYTHON ]0.10 #09sickn33/agentic-awesome-skills[ PYTHON ]0.019 #10cft0808/edict[ PYTHON ]0.0183 #16ZhuLinsen/daily_stock_analysis[ PYTHON ]0.0159 #24jundot/omlx[ PYTHON ]0.014

METRICS IN CONTEXT

MEDIAN ACROSS ALL 2559 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 14%

VELOCITY1.662.88-1.23ABOVE 9%

RETENTION0.9%6.3%-5.4 PPABOVE 2%

FORKS5,4221,183+4,239ABOVE 84%

SURPRISE0.000.00-0.00ABOVE 19%