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 · 60 shown
We study strategic liquidity provision in decentralized exchanges with concentrated liquidity as a mean-field game.
PAPER REPORTS · Margin-gated provision backtest on four Base pools, 7497 hours, September 2024 to July 2025: in the market 2.5–12% of…
Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents. If a simulator misprices this mechanism, agents learn policies that are optimal in the simulator but wrong in the real market.
The value of a forecast depends on its accuracy, but also on its actionability. In trading, an investor must translate return forecasts into positions while accounting for trading costs and the lingering impact of earlier trades.
OUR BACKTEST · Sharpe 0.07 · Return +8.8% · Max DD -55.7%
Classical execution models assume linear impact, diffusive prices, and an exogenous horizon. We study execution under concave power-law impact and Hurst-scaled price fluctuations, and make two contributions.
OUR BACKTEST · Sharpe -0.29 · Return -9.4% · Max DD -22.3%
We develop a framework to identify and quantify arbitrage across logically related prediction-market contracts.
PAPER REPORTS · Accumulated take, settled windows, 23 Jun-3 Aug 2026, net of spreads and taker fees at displayed depth, held to… · First take, settled windows, same period and costs: guaranteed return 2.7% ($1.10M on $40.6M); at resolution 3.2%…
Portfolio optimization is constrained by linear assumptions and limited integration of multi-modal information.
PAPER REPORTS · SBCA 2-asset (CAT, GILD), test 2021–2022, net of 0.25% one-way commission: final portfolio value 1.4392, annual return… · SBCA 4-asset (CAT, GILD, GS, KO), test 2021–2022, net of 0.25% one-way commission: final portfolio value 1.3564, annual…
OUR BACKTEST · Sharpe 2.62 · Return +54.1% · Max DD -10.1%
We study liquidity provision in automated market makers when trading in the external market incurs proportional transaction costs. We consider both separately collected fees and fees retained in reserves.
In its traditional form, the smart order router only cares about price when deciding where to send a trade; send the order to the exchange currently showing the tightest spread.
PAPER REPORTS · Mean effective execution cost 6.561 bp (latency-aware router) vs 6.548 bp (price-only baseline). · Hit rate vs baseline: 2.2% of 14,400 held-out rows (latency-aware cheaper than price-only).
We develop a data-driven approach to dynamic portfolio selection that combines vine-copula simulation with reinforcement learning.
PAPER REPORTS · NN-vine-RL ensemble, 22 complete monthly holding periods within 31 Jul 2024–30 Jun 2026 decisions: CAGR 34.13%, net of… · Sharpe ratio 2.309 (zero annual risk-free rate), same sample and costs.
To extend conventional model-level feature importance to economically meaningful portfolio outcomes and decisions, we propose a local first-order attribution-propagation framework that maps allocation-function feature exposures to local sensitivities of…
PAPER REPORTS · XGB baseline, OOS 2006-2024: net Sharpe 0.6175 (annualised, 5bp per unit turnover); gross Sharpe 1.0207; net mean 2.55%… · FFN baseline, OOS 2006-2024: net Sharpe 0.5750 (5bp); gross Sharpe 1.3051; net mean 2.65% p.a.; net FF5 alpha 1.12%…
OUR BACKTEST · Sharpe -0.82 · Return -24.2% · Max DD -31.5%
FLEX options are customized exchange-traded contracts allowing participants to choose nonstandard strikes, expirations, exercise styles, and settlement terms while retaining central clearing.
PAPER REPORTS · Rich-IV short straddle, research proxy (0.85 haircut, event close): N 40, mean P&L 1.5350% per trade, win rate 80.0%,… · Rich-IV short straddle, execution-stressed (1.25× median chain relative spread + $0.65/contract × 4 legs): N 40, mean…
When a trader executes a large order, the relevant question is not \emph{what will the price be?} but \emph{what would the price have been had I not traded?} Market impact is thus a causal quantity, yet classical models (Almgren--Chriss, propagators) regress…
Structural price diffusivity explains many empirical regularities of market impact including the ``square-root law'' and its crossover to a linear regime for low trading rates \citep{bonart2026diffusive}.
As option markets grow and AI advances, agentic systems for option trading are gaining increasing attention.
PAPER REPORTS · Total return 18.32% over 2025-03-03 to 2025-08-29 (six-month out-of-sample), 10 underlyings; fills at bid-ask midpoint… · Annualized Sharpe ratio 1.60 (same period and costs)
The square-root impact law (SRIL), $I = Yσ\sqrt{Q/V}$, bundles two facts that a single mechanism must explain at once: a shape (impact proportional to square-root of traded volume $Q$) and an amplitude ($Y=O(1)$, independent of the participation rate…
Abstract Using Gate.io hourly spot-order-book archives from January 2022 through June 2023, this paper reconstructs a long-horizon five-second panel for comparing the direct Ether/Tether (ETH/USDT) quote with the synthetic Ether/Bitcoin (ETH/BTC) $$\times $$…
Trade-sign errors can change measured trading costs even when classification accuracy is high. We validate the side of Polymarket's public trade prints against the taker leg of each print's on-chain settlement.
Factor mining seeks to discover signals from financial data that predict future asset returns and guide portfolio construction. Automated factor mining now spans genetic programming, reinforcement learning, generative models, and large language model agents.
Flashblocks divide a block's priority gas auction into shorter sequential auctions that commit transaction order before the block is complete. We ask how this auction cadence affects bidding and competition among automated arbitrageurs, or searchers.
We study finite-horizon portfolio optimization with proportional transaction costs and trading opportunities arriving at the jump times of a Cox process.
OUR BACKTEST · Sharpe 0.52 · Return +0.0% · Max DD -0.0%
In this paper, we extend earlier findings of supra-competitive outcomes in optimal-execution games by identifying a learned punitive mechanism that deters deviations and provides behavioural evidence of collusion.
Bank treasury portfolios must balance yield, liquidity, and interest-rate risk across bonds of different maturities.
PAPER REPORTS · DP mean terminal wealth over 6 months, starting from 1 (simulated DNS-VAR chain, unconditional-mean initial curve):… · DP mean terminal wealth over 12 months: 1.1801 at c=0; 1.1166 at c=0.01.
We model market impact as the response to submitted order flow net of counterflow from latent traders, activated when price displacements from the level that would prevail without the order exceed individual thresholds.
Hedging a derivative by trading the underlying asset changes the payoff that the hedging intended to replicate. We study this phenomenon when trading generates price impact and execution costs.
OUR BACKTEST · Sharpe -0.03 · Return -1.8% · Max DD -19.0%
Abstract Binary direction classifiers can appear stable on one chronological split while offering little predictive or economic value out of sample.
PAPER REPORTS · Full AND-gate (LightGBM + trend + Hurst), 3 expanding walk-forward folds, Mar-May 2025, 9 configurations: precision… · Full AND-gate unlevered next-bar accepted-signal mean return: -0.16 bps at 0 cost, -10.16 bps at 10 bp round-trip cost,…
This paper investigates cost-sensitive online window size selection for portfolio management under changing market conditions.
PAPER REPORTS · Hedge, DJIA 2021/03/04-2024/02/25, net of c=0.001 turnover cost: cumulative return 41.6977%, MDD -12.6326%, annualized… · Fixed Share, DJIA 2021/03/04-2024/02/25, net of c=0.001: cumulative return 38.1074%, MDD -12.9282%, annualized Sharpe…
The equal-weighted portfolio is a passive, rule-based strategy that has historically been difficult to outperform, delivering higher returns than the capitalization-weighted "market" benchmark across many markets and periods.
PAPER REPORTS · Mean-reverting frictional λ*,mr, 1995–2024 monthly, net of 15bp proportional costs: - cumulative net return 44.92 -… · Trending frictional λ*,trend, 1995–2024, net of 15bp costs: - cumulative net return 31.41 - return 0.13, volatility…
OUR BACKTEST · Sharpe 0.24 · Return +0.0% · Max DD -0.0%
Language-model agents now run the whole of quantitative factor research: they propose investment factors, backtest them, select the survivors and retire them. We ask which of those jobs an agent should keep.
PAPER REPORTS · Certified (frozen-referee) book, 4-family library, 20 groups of 5 seeds, campaigns starting 2016-2019 through 2026-08:… · Deflated Sharpe ratio 0.49-0.69 against 108 groups.
Stock price forecasting is a long-standing challenge in computational finance, driven by the inherent randomness of markets and complex temporal patterns.
PAPER REPORTS · CSI300 test (2017-01-01 to 2020-08-01), Qlib top-50 long, 20 replacements/day: excess annualized return 0.1809, excess… · CSI500 test (2017-01-01 to 2020-08-01), same strategy: excess annualized return 0.1529, excess information ratio…
Financial language models can transform unstructured firm-specific news into structured decision signals, but financial AI research lacks an integrated deployment framework for evaluating whether those signals remain useful in financial decision systems.
PAPER REPORTS · Long-short net Sharpe 2.85 (LLaMA-3, value-weighted quintile, net of 5bp one-way costs, 10% ADV cap, Jun 2024-Jan 2026) · Mean daily net return 0.34%, daily vol 1.89%, max drawdown -12.3%, cumulative long-short return 180% (LLaMA-3, same…
Abstract This paper studies how pre-trade transparency is associated with market quality in corporate bond markets.
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)
This study integrates the Black-Litterman (BL) model with deep learning techniques to construct a stock portfolio that incorporates investor sentiment.
PAPER REPORTS · BERT_BL, 2024-07-11 to 2024-12-31 (117 trading days), zero transaction costs: annualized return 106.58%, Sharpe 2.64,… · BERT_BL, same period, net of 0.03% commission + 0.1% sell stamp duty: annualized return 51.87%, Sharpe 1.55, Sortino…
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%…
Reinforcement learning trading systems published in the academic literature overwhelmingly rely on price-aggregate state representations (OHLCV bars) or limit-order-book depth features, leaving microstructure pattern theories from the practitioner literature,…
PAPER REPORTS · TSLA: +163.6% ROI, -27.5% max drawdown, 27,019 trades, held-out final 12 months of Jan 2020-Feb 2026 data, zero… · NVDA: +116.5% ROI, -47.8% max drawdown, 12,892 trades, same held-out 12-month partition, zero leverage, $0.0002/share…
For more than four decades, the 60/40 stock/bond portfolio has served as a benchmark for delivering reasonable returns without excessive risk. More recently, a 50/30/20 stock/bond/alternative portfolio has been suggested.
PAPER REPORTS · Markowitz: 11.6% annualized return, 9.0% annualized volatility, Sharpe 1.08, max DD 18.1%, mean DD 3.0%, turnover… · Simple Markowitz: 10.4% return, 9.3% volatility, Sharpe 0.91, max DD 15.8%, turnover 278.9%, same period and costs
OUR BACKTEST · Sharpe 0.43 · Return +18.9% · Max DD -16.4%
Transaction costs can make or break a trading strategy, particularly in relative-value trading of commodity and macro markets, where edges are a few basis points. Price impact is a central component of transaction cost.
PAPER REPORTS · Net P&L, monthly average over 2004-2011 (96 months), in basis points of $1B gross limit, after simulated impact cost…
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 study whether nuclear and energy-adjacent equity options exhibit a harvestable variance risk premium. Using CRSP and OptionMetrics data for 2000-2024, we construct a systematic cash-secured short-put strategy on a curated universe of nuclear-related firms.
PAPER REPORTS · EW put unconditional, 2000-2024 (300 months): 18.7% annualized return, 2.4% annualized volatility, Sharpe 7.81, MaxDD… · CAP-10 unconditional: 18.6% return, 2.4% vol, Sharpe 7.79, MaxDD 0.0%
Small-cap-inclusive equity universes contain recently listed and intermittently traded securities, so enforcing a common look-back discards a substantial fraction of the available information.
PAPER REPORTS · Annualized five-session volatility 11.17%, January 2000 - December 2025, net of all modeled execution costs… · Sharpe 0.814, same period, net of execution costs
Classical option-hedging methods like Black-Scholes delta assume constant, free rebalancing, which real markets don't allow. Deep hedging trains a neural network to handle these frictions directly, and prior work reports strong results.
PAPER REPORTS · Whalley-Wilmott (paper's best strategy), test period Sep 2023-Dec 2024, 11,546 episodes, 5bp round-trip cost: mean… · Whalley-Wilmott cost saving vs BS delta: -$1.79 per episode, 95% CI [-2.21, -1.39], p < 0.0001 (test period, 5bp cost)
Large language models (LLMs) are increasingly used to discover trading strategies, and much of the resulting literature shares a methodological weakness: many candidate strategies are generated, the best is reported, and neither look-ahead bias nor the…
PAPER REPORTS · Best gpt-4.1 discovery (E3, RSI x volume, 453-stock universe): design Sharpe 1.69 (2017-2021), evaluation Sharpe 0.18… · Best claude-sonnet-5 discovery: design Sharpe 0.44 (2017-2021), evaluation Sharpe -0.33 / -29% (2022-2025), DSR 0.18,…
OUR BACKTEST · Sharpe -0.10 · Return -10.8% · Max DD -47.8%
At 15-minute horizons, directional mean reversion is far stronger and more pervasive in cryptocurrency markets than in US equities: scored under one matched, strictly out-of-sample protocol, 90% of 183 Binance pairs carry significant directional reversal…
PAPER REPORTS · Gross edge per trade peaks near 1.3 bp of notional (BTC/ETH, 15m, 2025-01 to 2026-02) against a 5 bp cheapest maker… · Directional accuracy rises monotonically with confidence threshold, clearing 56% on the most confident bars (BTC/ETH);…
We study discrete-time asset pricing with bid-ask spreads and model uncertainty. The family of probability measures enters the no-arbitrage condition through the union of its supports.
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%
Abstract Market timing models aim to anticipate short-term market movements according to a given source of information. Such information could be extracted from an analysis of history or a forecast of the future.
PAPER REPORTS · S&P500 timing, 2018: index -6.7% annualized; Strat1-L 3.8%, Strat1-LS 14.3%, Strat2-L 0.8%, Strat2-LS 8.2% (no… · S&P500 timing, 2023: index 21.6%; Strat1-L 21.9%, Strat1-LS 22.1%, Strat2-L 25.5%, Strat2-LS 29.4% (no transaction…
OUR BACKTEST · Sharpe 0.61 · Return +49.0% · Max DD -31.2%
Reinforcement learning has gained increasing attention as a data-driven approach for stock trading. However, learning a policy that is both profitable and stable remains challenging due to non-stationary market behaviour and noisy reward signals.
PAPER REPORTS · DJI (test 1 Jan 2024 - 31 Mar 2025, 0.1% transaction fee both sides): annual return 21.785%±1.42, cumulative return… · FTSE (same period and costs): annual return 19.164%±1.36, cumulative return 24.596%±1.79, Sharpe 1.124±0.08, max…