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
Model Pruning for Low-Latency Trading Inference
Magnitude and structured pruning, the Lottery Ticket Hypothesis, movement pruning, distillation and 2:4 sparsity — the methods behind shrinking a trading model, and what still has to be measured before any of it ships.
Updating the Volume Curve Intraday: Does Adaptive Forecasting Actually Help?
Our VWAP article shipped a static, weekly-refit volume curve and called the forecaster the weakest link. This is the follow-up: a Bayesian intraday updater run against the same 500-parent BTCUSDT harness, with the IS delta conditioned on realized curve error.
Koopman Operators and DMD: Do Market Modes Survive Out-of-Sample?
Dynamic Mode Decomposition fits a linear operator to nonlinear market dynamics. The only question that matters: do the fitted modes persist from one window to the next, and does the rolling spectral radius lead realised volatility? Here is the measurement protocol and the code to run it.
Knowledge Distillation: Compressing Trading Models for Low-Latency Deployment
The blog's standing answer to the accuracy-vs-latency tension is a two-stage fast/slow split. Distillation is a different answer: train one small model to mimic the ensemble. The KD loss, temperature, born-again nets, early exits for a variable latency budget, and the distill-to-FPGA pipeline — plus the measurements that would decide whether it beats the two-stage split.
The Other Way a Regression Lies: Endogeneity, 2SLS, and the Gamma Calibration Problem
Selection bias in the search is not the only way a regression fools you. When the regressor is correlated with the error, more data makes the estimate more confidently wrong. Instrumental variables applied to the one endogeneity problem this blog has already left open: permanent impact from net taker flow.
Hawkes Processes for Order Arrival and Market Event Modeling
Fitting a self-exciting point process to real crypto trade tape: where the three numbers (mu, alpha, beta) come from, how to estimate the branching ratio n, whether the exponential kernel survives a goodness-of-fit test, and how much n moves when you change the estimation window.
Hamiltonian Neural Networks: Does a Financial System Conserve Anything?
Hamiltonian Neural Networks are provably stable — but stability is worthless if the conserved quantity does not exist. Learning a scalar H via autograd, symplectic integration, and the falsification test that decides whether a financial (q, p) pair is canonical at all.
Toda-Yamamoto vs Differenced Granger: Does the BTC Lead-Lag Survive?
Granger causality on crypto prices done two ways — differenced returns and Toda-Yamamoto on levels — with a correct Wald implementation, an effective-N corrected causality matrix, and a rolling-stability test of whether the lag is tradeable at all.
비모수적 가격 모델링을 위한 가우스 프로세스
금융 시계열을 위한 커널 설계(모계 거칠기, 국지적 주기 구성, 스펙트럼 혼합) 및 검증 세트가 필요 없는 정규화 도구로서의 한계 가능성. 게다가 거래 가능하기 전에 측정해야 할 사항에 대한 정직한 목록도 있습니다.
PDE 기반 금융 모델링을 위한 푸리에 신경 연산자
연산자 학습은 포인트가 아닌 전체 기능 공간을 매핑합니다. 푸리에 신경 연산자가 주파수 공간에서 PDE 솔루션 연산자를 매개변수화하는 방법, 옵션 가격 책정을 위해 무엇을 구매하는지, 실제 하드웨어에서 여전히 측정이 필요한 주장은 무엇인지를 매핑합니다.
하루 종일 컨텍스트가 10분 컨텍스트보다 낫습니까? 플래시 어텐션과 시퀀스 길이 질문
Flash Attention은 타일링, 온라인 소프트맥스 및 N^2 d^2 / M의 IO 경계 등 23,400단계 거래 컨텍스트를 계산적으로 자유롭게 만듭니다. 긴 컨텍스트가 모델을 더 좋게 만드는지 여부는 별도의 질문이며 주장할 것이 아니라 측정해야 합니다.
앙상블 방법: 강력한 알파를 위한 약한 학습기 결합
이 블로그에서 다루지 않은 앙상블 거래에 대한 세 가지 사항: 모델 개수가 아닌 공분산 항이 앙상블 오류를 지배하는 이유, 스택이 아웃 오브 폴드 메타 기능을 갖춘 신호 결합 레이어로 작동하는 방식, 여러 신호에 걸친 회전율 상쇄가 실제로 실행 비용을 줄이는지 여부입니다.