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.
Articoli
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.
Processi gaussiani per la modellazione dei prezzi non parametrica
Progettazione del kernel per serie temporali finanziarie - rugosità Matern, composizione periodica locale, miscele spettrali - e verosimiglianza marginale come regolarizzatore che non necessita di un set di validazione. Inoltre, l'elenco onesto di ciò che deve ancora essere misurato prima che tutto ciò sia commerciabile.
Operatore neurale di Fourier per la modellazione finanziaria basata su PDE
L'apprendimento degli operatori mappa interi spazi funzionali, non punti: come l'operatore neurale di Fourier parametrizza un operatore di soluzione PDE nello spazio delle frequenze, cosa acquista per il prezzo delle opzioni e quali delle sue affermazioni necessitano ancora di essere misurate su hardware reale.
Un contesto di un'intera giornata batte uno di dieci minuti? Attenzione flash e domanda sulla lunghezza della sequenza
Flash Attention rende computazionalmente gratuito un contesto di trading di 23.400 passaggi: affiancamento, softmax online e un limite IO di N ^ 2 d ^ 2 / M. Se quel contesto più lungo renda il modello migliore è una questione separata e deve essere misurato, non affermato.
Metodi d'insieme: combinare studenti deboli per un alfa robusto
Tre cose sugli insiemi di trading che questo blog non ha trattato: perché il termine di covarianza – e non il conteggio dei modelli – domina l'errore dell'insieme, come lo stacking funziona come uno strato di combinazione di segnali con meta-caratteristiche out-of-fold e se la compensazione del turnover tra molti segnali riduce effettivamente i costi di esecuzione.