Research
Every research paper we have written up, newest paper first. New arrivals are screened automatically for topical fit with systematic trading; the ones that clear it are read, written up, and — where the idea is testable on our data — backtested. Particular focus on alpha hypotheses that can be formalised and tested. The Radar also covers portfolio construction, market risk and execution where the research is directly relevant to systematic investment processes. Follow new entries by RSS.
16,915 papers screened · 588 on the radar · 138 shown
We investigate the systemic macroscopic dynamics emerging from Limit Order Books (LOBs) populated exclusively by autonomous reinforcement-learning agentic traders.
We develop a model-agnostic framework for noise reduction in high-dimensional time series that explicitly targets optimal recovery of a low-dimensional latent dynamic component contaminated by observational white noise.
PAPER REPORTS · Macro panel one-step-ahead forecast (not a trading strategy): average MSE 23.47 (standard error 10.87) for VAR(2) on…
OUR BACKTEST · Sharpe -0.50 · Return -21.3% · Max DD -34.9%
Forecasters often score the same units per date against one standardized realized outcome. We show that every standardized forecast splits exactly into a component aligned with this common target and a component uncorrelated with it.
PAPER REPORTS · Three-way equal-weight selection, LLM equity panel, 157 weekly test dates Mar 2023–Jun 2026: relative-score risk 1.079,… · Three-way equal-weight selection, ETF panel, 196 monthly test dates (2005–2026 sample): relative-score risk 1.076,…
OUR BACKTEST · Sharpe 0.14 · Return +27.2% · Max DD -59.8%
Modeling the dynamics of option implied volatility surface (IVS) is crucial for pricing, hedging, and risk-managing option portfolios.
Mitigating \emph{drawdown}, the decline in wealth from its running peak, presents a canonical problem in path-dependent risk control.
PAPER REPORTS · Figure 1 reports higher estimated expected terminal return E[R_pi] for the drawdown-modulated policy than for the… · Maximum drawdown is guaranteed by construction: P(d* <= d_max) = 1 and V(k) >= (1 - d_max)V_max(k) > 0 for all k with…
OUR BACKTEST · Sharpe -1.60 · Return -0.0% · Max DD -0.0%
Catastrophe (cat) bonds overcome some lack of reinsurance by sourcing capacity from the wider capital markets. We present a new type of cat bond addressing the known trade-off between moral hazard and basis risk.
PAPER REPORTS · Cat bond tranche A (attachment 7.861e9 = modeled 100-yr, exhaustion 11.008e9 = modeled 200-yr), extremal-t Cauchy… · Tranche B (attachment 9.593e9 = modeled 150-yr, same exhaustion), same parameters: price 100.69 EUR; par-implied spread…
The standard Euler discretization schemes for numerical option pricing under stochastic volatility models are known to exhibit high biases and potential unreliability.
We develop an efficient Monte Carlo simulation scheme for pricing options under the Ornstein-Uhlenbeck driven stochastic volatility model via the operator splitting approach.
In a statistical factor model, principal components (or eigenvectors) of a sample covariance matrix serve as estimates of {\it principal directions}, the true drivers of co-movement of a collection of observed variables.
OUR BACKTEST · Sharpe 0.52 · Return +30.7% · Max DD -31.0%
This paper develops inference for a Gaussian-nested hypergeometric family of distribution functions.
Automated execution algorithms are organized into schedule-based and liquidity-seeking families.
PAPER REPORTS · Relative slippage vs. arrival mid, passive Shadow-PPOV: +0.0955 ± 0.0130 ticks/contract (CME ES, calendar 2025, 246… · Relative to immediate execution: −0.4236 ± 0.0117 ticks/contract (same sample and cost assumptions)
We present SAiFE_gym, a Python module that provides a collection of simulation environments for studying trading problems in Constant Product Markets (CPMs) with Concentrated Liquidity (CL).
PAPER REPORTS · Nominal PPO LP agent, mean terminal PnL (gas included, 2 units X per rebalance) = +55.43 at training domain… · Domain-randomized PPO LP agent, mean terminal PnL (gas included) = +55.38 at (sigma=0.03, alpha1=450); grid values span…
Retail proprietary-trading firms sell a two-stage product: a paid evaluation that must reach a profit target before breaching a trailing drawdown, then a funded account that must survive a minimum window and a consistency rule before a payout.
PAPER REPORTS · Adversarial implementation of a published practitioner rule set (not the authors' own edge, but the authors' own… · Best in-sample payout rate achievable by the authors' payout-rate optimisation: 4.6% (Lucid Flex) versus a 9.5%…
We develop a diffusion-model framework for dynamic implied-volatility surface generation and evaluate its economic usefulness through data-driven hedging. The framework consists of two models.
PAPER REPORTS · AD-Seq-Vol hedging, held-out 1 Jul 2018 - 28 Feb 2023, transaction costs included as half bid-ask spread in the… · AD-Seq-Vol, same period, COVID window (13 Feb - 21 Jul 2020) excluded: mean 0.78, median 0.02, std 8.33, 5% VaR 10.72,…
Stock price prediction remains challenging due to the non-stationary and noisy nature of financial time series.
PAPER REPORTS · S&P 500 2024 out-of-sample (365 days): total return 29.41%, Sharpe 1.43, Sortino 1.85, max drawdown -9.75%, win rate… · DJIA 2024: total return 21.44%, Sharpe 1.15, Sortino 1.75, max DD -8.94%, win rate 57.7%, 26 trades — vs buy-and-hold…
An ensemble of roughly 3,000 signals over 20 assets was reported to have approximately 90% correlation with the leading component of the asset-space return structure.
OUR BACKTEST · Sharpe -0.16 · Return -29.7% · Max DD -97.0%
In this note, we propose a general structural approach to model a default time $τ$ as the first-passage time (FPT) of a (``firm-value'') process $S$ below a (``debt'') barrier $K$ that comply with a pre-specified survival probability curve $G(t)=\Pr(τ>t)$.
Abstract This paper introduces a Coupled realised real-time EGARCH model with Filtered Historical Simulation (FHS), referred to as the “CouRTES” model, as an extension of the Realised EGARCH-type models for multi-horizon volatility and distributional…
PAPER REPORTS · QLIKE loss (realised measure target, 250 rolling origins, 30 May 2018 - 29 May 2019): lowest in 11/14 horizons within… · sMAPE (total log-return target): best in 9/14 horizons; mean improvement 0.84% vs Coupled GARCH(1,1) and 1.75% vs…
Classical market-making strategies based on stochastic control, such as the Avellaneda-Stoikov and the Guéant-Lehalle-Fernandez-Tapia (GLFT) extension, provide closed-form quoting rules, but rest on assumptions that break down at realistic microstructure…
PAPER REPORTS · Stationary flow: DQN risk-return frontier lies above the GLFT frontier throughout the observed risk range (N_sim = 1000… · Regime-switching (tau_r = 60 MO events, omega = 0.30, N_sim = 100 paired episodes of 100,000 LOB events): Algorithm B…
The Log S-fBM model, introduced by Wu et al., is a stochastic volatility model whose log volatility is a stationary fractional Brownian motion (S-fBM): a stationary Gaussian process with power-decaying autocovariance driven by the Hurst exponent $H$, and…
We study variance-optimal stock hedging and the convergence of approximate strategies in the rough Hawkes--Heston model.
We develop semi-closed pricing formulas and lifted-model hedging methods for discretely monitored geometric and arithmetic Asian options in the Volterra-Heston stochastic volatility model.
We develop a filter for time series, defined at each time $t$ as the minimizer of a discounted convex combination of observed and expected losses.
Pathwise differentiation of Monte Carlo estimators fails at payoff discontinuities, producing zero or biased sensitivities for barriers, autocallables, and digital options.
Herein, we propose a quantum circuit learning framework for modeling the realized volatility (RV) of Bitcoin and investigate the statistical properties of the predicted time series through multifractal analysis.
Abstract This study develops a robust framework for modeling dynamic volatility, asymmetry, and tail dependence in financial returns, focusing on the daily returns of Natural Resource Index () and the Oil and Gas Index ().
OUR BACKTEST · Sharpe 0.47 · Return +42.5% · Max DD -27.9%
Abstract Value-at-Risk (VaR), the most widely used measure of market risk, is typically evaluated through backtesting of point forecasts. Such procedures, however, say little about the uncertainty of the estimated quantile.
We study deep hedging in the context of dynamics risk measures, where sequential decisions are time-consistent.
PAPER REPORTS · Terminal hedging loss CVaR95% at 1-year maturity, 10,000-path test set with initial state perturbation, 0.1%… · Mean terminal P&L, same setup (alpha=95%): log -1.1143 (std 1.7095), static +0.2161 (std 2.6423)
Trade durations in high-frequency foreign exchange data exhibit increased occurrence near integer values. To address this empirical phenomenon, we propose the granularity-adjusted autoregressive conditional duration (GA-ACD) model.
This paper develops uniform inference and certified capacity decisions for an estimated financial stability boundary. Conditional risk, temporary cross-impact, and effective risk-bearing capacity are jointly estimated from dependent observations.
PAPER REPORTS · Capacity/regret under the baseline loss convention (simulated 60-cell design, no market data): Projected safe - planned… · Under the high convention-loss calibration: projected-safe mean regret 0.107, below pointwise delta 0.120 and plug-in…
This paper develops a mechanism through which costly changes in the representations used for portfolio choice can contribute to persistent signed order flow.
We propose a deterministic numerical method for pricing and hedging surrenderable equity-linked life-insurance contracts with periodic premiums and fund contributions, maturity and death guarantees, and Bermudan surrender under correlated stochastic…
Similar to banks, DeFi protocols expose depositors to operational risk (USD 9.45 billion across 1,075 events since 2020). Unlike banks, they are not required to hold capital against it. A protocol may maintain a buffer voluntarily.
Market-order flow in financial markets exhibits long-range correlations. This is a widely known stylised fact of financial markets. A popular hypothesis for this stylised fact comes from the Lillo-Mike-Farmer (LMF) order-splitting theory.
We introduce ISCOS, a cross-entropy importance-sampling calibration method for rare credit-portfolio losses. We derive Gaussian and Gaussian--inverse-Gamma proposals and analyse the propagation of finite-COS approximation errors to the fitted parameters.
Stablecoins, typically pegged to fiat currencies, cannot achieve true stability because they inherit fluctuations in the underlying unit of account.
PAPER REPORTS · USD evaluation, USD risk space: annualized return 0.117, annualized volatility 0.211, Sharpe 0.554, max drawdown… · USD evaluation, MLV risk space: annualized return 0.156, annualized volatility 0.223, Sharpe 0.699, max drawdown…
Bitcoin inverse options, traded on the Deribit exchange and settled in the underlying cryptocurrency rather than in fiat currency, combine extreme and genuinely rough volatility dynamics with a non-linear, currency-dependent payoff structure.
Abstract High-dimensional multivariate normal (MVN) integration is a computational bottleneck in many statistical applications, particularly in finance and econometrics.
Coupled feedback networks are often monitored channel by channel even though cross-channel paths alter both stability margins and transmitted disturbances.
PAPER REPORTS · Detection power 1.00 with false-alarm rate 0.12 on zero-coupling entries under independent regime-switching gains (n =… · Detection power 1.00, false-alarm rate 0.22, off-diagonal RMSE 0.28 under correlated staircase gains (same design)
Lead-lag relationships are widely used in financial time series, and many clustering algorithms based on them have been developed. The traditional DTW-KMedoids algorithm performs well both on the synthetic dataset and the real financial dataset.
PAPER REPORTS · Sharpe 0.866, annual return 6.21%, annual volatility 7.17%, max drawdown -63.908, hit rate 0.520, profit-loss ratio… · Sharpe 0.808 / 0.790 (KShape mod / med), lead strategy, 679 assets, same period; drawdowns -67.604 / -69.418
OUR BACKTEST · Sharpe 0.39 · Return +27.5% · Max DD -39.3%
Understanding the propagation of extreme events is important in many economic and environmental applications, yet most econometric methods for causal inference focus on average effects rather than tail behavior.
Implied volatility surfaces summarise the option market and are central to many financial applications.
PAPER REPORTS · Surface point-forecast RMSE aggregated over 30 horizons: 0.01262 vs persistence 0.01343, +6.09% gain; MAE gain +3.45%;… · h=1: RMSE 0.00619 vs persistence 0.00535 (-15.72%); MAE -34.49%
OUR BACKTEST · Sharpe -0.00 · Return -1.0% · Max DD -329.1%
The stability of markets hosting leveraged exchange-traded products is governed not by any single product's loop gain but by the spectral radius of a loop-gain matrix, and scalar per-product monitoring underestimates system feedback by construction.
A companion paper \cite{ItkinDF2026} introduced the Diagonal Frog (DF) positivity-preserving schemes for anisotropic Fokker--Planck equations, advancing each directional substep by a Krylov-computed matrix exponential, which dominates the cost.
Basket options are difficult to value under correlated lognormal dynamics because weighted sums and differences of lognormal variables have no tractable distribution.
Deep hedging is a data-driven approach to learn hedging strategies. It relies on synthetic price paths generator, as real market data is often limited for training.
OUR BACKTEST · Sharpe 1.78 · Return +5.9% · Max DD -0.6%
We study continuous-time dynamic portfolio optimization under a Conditional Value-at-Risk (CVaR) constraint on the investor's terminal loss.
PAPER REPORTS · Complete market, binding c = -0.94, T = 1 simulated: E[W_T] = 1.0242, CVaR_0.95(-W_T) = -0.9406, average exposure… · Complete market, nonbinding c = -0.86, T = 1 simulated: E[W_T] = 1.0322, CVaR_0.95(-W_T) = -0.8671, average exposure…
OUR BACKTEST · Sharpe 0.75 · Return +55.2% · Max DD -26.8%
We introduce Deep-MKV-TS, a path-dependent McKean-Vlasov framework for financial scenario generation. The stochastic dynamics are chosen by matching selected path and volatility features of generated scenarios to those observed in the data.
PAPER REPORTS · Frozen ES drawdown-risk decision, 123 held-out sessions (January-June 2026): Deep-MKV-TS average exposure 1.99 +/- 0.06… · Conditional-forecast CRPS (x1000, lower better) on the 123-session chronological held-out test, four-seed mean +/- sd:…
Automated market makers (AMMs) are a cornerstone of decentralised finance (DeFi). Constant product markets with concentrated liquidity, such as UniswapV3, are now a well-established design.
PAPER REPORTS · PPO_narrow, risk-neutral, sigma=0.01, g=2: mean PnL 49.91 +/- 0.38 USDC, 5% CVaR 9.15 +/- 0.65, over 1000 evaluation… · PPO, risk-neutral, sigma=0.01, g=2: mean PnL 42.31 +/- 0.97 USDC, 5% CVaR 6.08 +/- 0.97
We introduce a reinforcement learning framework for market making in a limit order book.
PAPER REPORTS · Normalized cash flow (20), noise market: LN mean 6.03, sd 2.81 (M=2); mean 4.66, sd 1.41 (M=20); 10,000 test episodes,… · Normalized cash flow, noise+tactical market: LN mean 9.11, sd 2.20 (M=2); mean 5.68, sd 1.03 (M=20)