Blog

Ijobiy kutilayotgan qiymatga ega strategiya ham, agar bet hajmi noto'g'ri tanlansa, hisobingizni yo'q qilishi mumkin. Biz Kelli mezonini formula chiqarilishidan strategiyalar portfeliga qadar ko'rib chiqamiz: nega to'liq Kelli xavfli, qismli Kelli yarim o'zgaruvchanlikda o'sishning 75% ni qanday beradi, va Kelli ulushi daromad va xavfni qanday o'zgartirishini ko'rsatadigan interaktiv kalkulyator.

ZhuLinsen tomonidan yaratilgan daily_stock_analysis loyihasiga chuqur nazar — A-aksiyalar, HK, AQSH va boshqa bozorlardan bozor ma'lumotlarini oluvchi, LLM orqali texnik va yangiliklar tahlilini o'tkazuvchi hamda har bir savdo kunida strukturalangan 'qaror paneli'ni messenjeringizga jo'natuvchi ochiq kodli tizim. Arxitekturasi, ma'lumot fallback mexanizmi, agent strategiyalari, cheklovlari.

How Google's Temporal Fusion Transformer brings interpretable multi-horizon forecasting to quantitative portfolio management, with attention-based variable selection, quantile outputs, and a worked pytorch-forecasting pipeline.

Qamrov kafolatlangan, taqsimotdan mustaqil bashorat intervallari. Savdo xavfini kalibrlash va pozitsiyalarni parametrik farazlarsiz o'lchamlash uchun split conformal, jackknife+ va adaptive conformal inference'dan foydalanamiz.

Decomposing and predicting bid-ask spreads with ML — from Roll's implicit estimator to gradient boosting and neural networks — with the units, leakage, and benchmarking pitfalls that bite in production.

DeepLOB CNN, inception moduli va LSTM ni birlashtirib, xom order book ma'lumotlaridan mid-price harakatlarini qanday bashorat qiladi — arxitektura, haqiqiy FI-2010 raqamlari va ishlaydigan PyTorch qayta implementatsiyasi.

A deep dive into Pipeline — the composite allocation algorithm we built on top of HRP. Hierarchical Risk Parity as the base, a long/short overlay driven by agent signals and confidence, and a final risk correction via CVaR with a Hull-White volatility adjustment. The full math from our spec, plus the actual Rust implementation.