Eugen Soloviov
Trading-systems engineer
Trading-systems engineer building bots since 2017: cross-exchange arbitrage (connected up to 30 venues), cointegration-based pairs arbitrage across spot and futures, scalping, news and sentiment-driven strategies, trend algorithms, and portfolio management and balancing algorithms. Also builds sub-millisecond order execution, big-data warehouses, backtesting engines, AI agents, and trading interfaces (incl. open-source profitmaker.cc). Stack: JS/TS, Python, Rust/Zig/Go, DevOps, backend, frontend, architecture.
Articles
Jesse: Python va Rust tilidagi daqiqalarga asoslangan dvigatelli kripto algo-treyding freymvorki
Jesse — kripto bozorlari uchun algo-treyding freymvorkiga chuqur sharh. Daqiqalarga asoslangan simulyatsiya, holat mashinasi sifatidagi strategiyalar, Rust bilan tezlashtirilgan indikatorlar, overfitting'dan himoyalangan optimallashtirish va ochiq manbali yadro bilan jonli treyding o'rtasidagi chegara.
AI Hedge Fund: sun'iy intellekt tahlilchilari savdolar bo'yicha ovoz beradigan ko'p agentli fond
virattt tomonidan yaratilgan AI Hedge Fund-ga chuqur nazar — bu ochiq kodli tizim bo'lib, unda turli tahlil uslublariga ega bir nechta LLM agenti xavf filtri orqali portfel quradi. Arxitekturasi, agentlari, cheklovlari va haqiqiy tizimlar uchun saboqlar.
AI4Finance Foundation: Algo-treyding uchun FinGPT, FinRL va FinRobot ekotizimi
AI4Finance Foundation ekotizimi bo'yicha to'liq qo'llanma: FinGPT (moliya uchun LLM + LoRA), FinRL (treyding uchun kuchaytirilgan o'qitish), FinRobot (ko'p agentli orkestrlash). Sun'iy yo'ldoshlar, quvurlar va amaliy foydalanish.
VectorBT: The Fastest Backtesting Framework for Python
Overview of VectorBT — an innovative quantitative analysis library that changes the approach to backtesting thanks to the power of NumPy and Numba.
Kripto portfellarida birgalikdagi xavfni modellashtirish uchun kopula modellari
Chiziqli korrelyatsiyadan tashqarida — kriptovalyuta portfellarida aniq VaR va CVaR bahosi uchun dum bog'liqligi va birgalikdagi xavfni aniqlash uchun kopula modellaridan foydalanish.
ZigBolt: Why We Built Our Own Aeron in Zig and Hit 20 Nanoseconds Per Message
How and why we built an ultra-low-latency messaging system for HFT from scratch in Zig. No JVM, no GC, no surprises. SPSC ring buffer at 20 ns, IPC at 30 ns, codec at 0 ns. With benchmarks.
ETF portfelini avtomatik qayta balanslash: Tinkoff Invest uchun botni qanday yaratdik
Tinkoff Invest'da ETF portfelini avtomatik qayta balanslash uchun ochiq kodli TypeScript/Bun bot. Toʻrtta balanslash rejimi, marja savdosi, koʻp hisobli qoʻllab-quvvatlash. Manba kodi bilan.
Aeron: HFT sohasining yarmini harakatga keltiruvchi xabar almashish tizimining ichki tuzilishi
Aeron'ga chuqur nazar — yuqori chastotali savdo uchun Real Logic kompaniyasining xabar almashish tizimi. Transport, Archive, Cluster, Sequencer. Ichida nima bor, u qanday ishlaydi va to'siqlar qayerda.
How to Catch Drops After Shitcoin Pumps: A Systematic Approach
A systematic breakdown of shorting strategies after shitcoin pumps. Funding rate, OI, volume analysis, candlestick patterns, liquidation cascades. With a practical algorithm.
Algoritmik Treydingda Order Turlari: Chasing bilan Limitdan Virtual Orderlargacha
Algoritmik treydingdagi order turlari haqida to'liq qo'llanma: standart birja orderlari, chasing limit, vaqtga asoslangan orderlar, virtual/sintetik orderlar. Kod misollari va real foydalanish holatlari bilan.
Algoritmik treyding uchun bar turlari va agregatsiya usullari
Sham qurilishining ikki o'qli tasnifi: 17 asosiy bar turi (vaqt, tik, hajm, dollar, Renko, diapazon, o'zgaruvchanlik, Heikin-Ashi, Kagi, Line Break, P&F, TIB, VIB, seriya, CUSUM, entropiya, delta) × 3 agregatsiya usuli (kalendar, siljuvchi, moslashuvchan) = 51 kombinatsiya. Amalga oshirish kodi va amaliy tavsiyalar bilan.
Hidden Markov Models in Trading: How to Adapt Your Strategy to Market Regimes
How to identify the current market regime (bull, bear, sideways) using Hidden Markov Models and automatically switch trading strategies. With Python code and backtests.