On 21 Nov 2024 Adani fell 22.61%. My model didn't know why, and it wasn't allowed to guess.
Описание и применение
Ghost Candles – инструмент, который определяет, насколько неожиданным был день в истории акций, используя только исторические данные и модели TabPFN. Он выделяет «призрачные» дни, генерирует короткие истории и сравнивает эффективность с классическим нормальным распределением.
Задача
Determine how unexpected a stock move was based solely on its historical data, without external news or explanations.
Результат
Ghost Candles accurately flagged a small number of truly abnormal days (e.g., Adani’s 22.61% drop on 21 Nov 2024) while keeping false positives low, outperforming a simple bell‑curve baseline.
Рабочий процесс
- Collect 750 days of historical price data for a stock
- Transform each trading day into a 17‑column feature table (returns, volatility, volume, distance from 50‑day average, etc.)
- Use TabPFN‑3.5 to predict 20‑day ahead quantile ranges for each day
- Slide the prediction window forward to generate 671 forecast days per stock
- Flag days whose actual return lies outside the 98% prediction band as ghosts
- Classify ghosts as Poltergeist (odds 1 in 100 or worse) or Wraith (outside the band edge)
- Generate a short ghost story with Google’s Gemma via Ollama, obeying the rule that no reason can be given
- Render results on a web page with a chart of glowing dots, cards, and an honesty check on the Oracle
Доказательства
TabPFN expected 21 November 2024 to land somewhere between −9.92% and +8.98%. It fell 22.61%, on 19.8 times the usual trading volume.
TabPFN makes this cheap. It’s pretrained on millions of made‑up tables and learns a new table just by reading it, so there’s no training and I didn’t tune a single setting.
Adani Enterprises, 671 forecast days: Ghosts flagged (pure luck would give about 7) – TabPFN 4, Bell curve 24.
- Дата записи: 2026-11-01T11:13:53.860Z