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
+702% on SOL. Where Is Jev in This Backtest?
We ran a trend strategy across 15 crypto pairs, checked costs and access to future candles, and tested Jev separately. Where did profits appear, and why can't we promise them in live trading yet?
XGBoost for Return Direction: Class Imbalance and Decision Thresholds
Return-direction classifiers are imbalanced problems, and 0.5 is the wrong decision threshold. Comparing scale_pos_weight, focal loss, and precision-constrained threshold optimization on crypto data — plus the engineering differences between XGBoost, LightGBM, and CatBoost.
Transfer Entropy: Which Way Does Information Flow Between Crypto Assets?
DCC-GARCH tells you when crypto dependence tightens. Transfer entropy tells you which way it points. A directed information-flow measure, its null calibration, and an honest account of what it does and does not add over average pairwise correlation.
Trade Classification When You Have No Side Flag: Tick, Quote, Lee-Ready, BVC
Reconstructing trade direction from OHLCV, bar history, or venues without an aggressor flag — the classic rules, the stale-quote problem, bulk volume classification, and how to measure them against crypto's free ground truth.
Tiempo irregular en modelos de ticks: codificaciones de tiempo continuo versus incrustaciones posicionales simples
Los modelos de secuencia alimentados con datos de ticks aún suponen un espaciado regular. Tres formas de decirle a un Transformer cuándo ocurrió realmente un tic (codificación continua en escala de tiempo que se puede aprender, estado latente ODE-RNN y delta_t como característica simple) y la ablación que decide entre ellas.
Synthetic Control Methods for Evaluating Trading Strategies
This series has priced the selection route to a false edge — DSR prices the winner, PBO prices the search. Neither touches confounding: the strategy that made money because volatility doubled the week you deployed it. The Synthetic Control Method builds a weighted counterfactual from a donor pool of untouched instruments and gives you a falsification criterion and a placebo p-value.
Puntuación de pronósticos probabilísticos: CRPS, calibración PIT y DeepAR
Cómo evaluar honestamente una distribución predictiva: CRPS como regla de puntuación adecuada, el histograma PIT como diagnóstico de calibración y muestreo DeepAR en GluonTS.
Redes neuronales basadas en la física para la fijación de precios de opciones
Poner las PDE de fijación de precios de Heston, de límite libre y de difusión de salto en una pérdida de red neuronal: el residuo del precio logarítmico, el truco de la autograduación parcial mixta y lo que aún necesita medirse.
PCMCI: Causal Discovery in Multivariate Crypto Time Series
How PCMCI's two-stage MCI test recovers directed causal links between crypto assets where correlation and bivariate Granger cannot — the construction, the tigramite pipeline, and the real-data study it still needs.
Order Flow Imbalance: The Cont-Kukanov-Stoikov Event Decomposition
Turning raw book updates into a signed flow quantity: the CKS event decomposition, multi-level OFI with PCA reduction, and Lee-Ready trade classification — plus an honest accounting of what the headline R-squared actually measures.
Neural ODEs: Does Continuous Time Beat a Delta-Time Feature?
Neural ODEs, Neural SDEs and continuous normalizing flows for irregularly-sampled market data — and the one ablation that decides whether continuous dynamics are worth their solver cost.
Multi-Task Learning for Simultaneous Price, Volume, and Volatility Prediction
Does jointly predicting return, volume, and volatility actually help? Measuring loss-balancing schemes and diagnosing negative transfer through gradient cosine similarity — with a classical baseline and purged walk-forward folds.