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.
Gaußsche Prozesse zur nichtparametrischen Preismodellierung
Kernel-Design für Finanzzeitreihen – Matern-Rauheit, lokal periodische Zusammensetzung, Spektralmischungen – und die Grenzwahrscheinlichkeit als Regularisierer, der keinen Validierungssatz benötigt. Dazu die ehrliche Auflistung dessen, was noch gemessen werden muss, bevor etwas davon handelbar ist.
Neuronaler Fourier-Operator für PDE-basierte Finanzmodellierung
Das Lernen von Operatoren bildet ganze Funktionsräume ab, nicht Punkte – wie der neuronale Fourier-Operator einen PDE-Lösungsoperator im Frequenzraum parametrisiert, was er für die Optionspreisgestaltung kauft und welche seiner Ansprüche noch auf realer Hardware gemessen werden müssen.
Ist ein ganztägiger Kontext besser als ein zehnminütiger Kontext? Flash Attention und die Frage nach der Sequenzlänge
Flash Attention macht einen Handelskontext mit 23.400 Schritten rechenfrei – Kacheln, Online-Softmax und eine IO-Grenze von N^2 d^2 / M. Ob dieser längere Kontext das Modell besser macht, ist eine separate Frage und muss gemessen und nicht behauptet werden.
Ensemble-Methoden: Kombination schwacher Lernender für robustes Alpha
Drei Dinge über den Handel mit Ensembles wurden in diesem Blog nicht behandelt: Warum der Kovarianzterm – und nicht die Modellanzahl – den Ensemblefehler dominiert, wie Stacking als Signalkombinationsschicht mit Out-of-Fold-Metafunktionen funktioniert und ob die Umsatzverrechnung über viele Signale hinweg tatsächlich die Ausführungskosten senkt.