stefan-jansen/machine-learning-for-trading — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #2153 · UNIT ID 132754148

stefan-jansen/machine-learning-for-trading

Code for Machine Learning for Trading, 3rd edition — from data sourcing to live execution.

[ JUPYTER NOTEBOOK ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.000333

ENGAGEMENT0.48

FRESHNESS1.34

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

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

2% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

1.71

ACCEL

-0.01

RETENTION

9.8%

PEAK 2026-02-23 · FORK-RETENTION 68.0% · 307 STARS / WINDOW

Author Audience

AUDIENCE

5,075

FOLLOWERS

2,711

OWNER ★

23,644

Engagement Signals

FORKS

5,408

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 305 / 307 (DIVERSITY 0.99)

Why This Is A Finding

stefan-jansen/machine-learning-for-trading собрал 307 звёзд за окно, тогда как у автора всего 2,711 подписчиков — эффективная аудитория ≈ 5,075. Это даёт surprise-индекс 0.000333 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 68.0% и 2 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 28% OF 2987 FINDINGS

#267pageman/sutskever-30-implementations[ JUPYTER NOTEBOOK ]0.00627 #293Lordog/dive-into-llms[ JUPYTER NOTEBOOK ]0.00576 #496lyogavin/airllm[ JUPYTER NOTEBOOK ]0.00444 #678duoan/TorchCode[ JUPYTER NOTEBOOK ]0.00336 #704CalvinXKY/InfraTech[ JUPYTER NOTEBOOK ]0.0032

METRICS IN CONTEXT

MEDIAN ACROSS ALL 2987 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 28%

VELOCITY1.712.84-1.14ABOVE 13%

RETENTION9.8%6.8%+3.0 PPABOVE 63%

FORKS5,4081,068+4,340ABOVE 85%

SURPRISE0.000.00-0.00ABOVE 33%