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 · 37 shown
PAPER REPORTS · DCC-ePOET-1, out-of-sample global MVP on 331 S&P 500 stocks: Var 0.445, Annual-SD 10.840, mean Sharpe ratio 2.281,… · DCC-ePOET-2 (latent factors only, no observable factors), same setup: Var 0.464, Annual-SD 11.049, mean Sharpe ratio…
Although advances in artificial intelligence (AI) and machine learning (ML) have transformed financial risk assessment, many early-warning frameworks for systematic risk still rely on isolated macro-financial indicators with limited integration of established…
Introduction & purpose Capital structure is an important determinant of investment decision as it influences share price as well as the overall earnings of the firm.
PAPER REPORTS · SMB (small minus big, equal-weighted, 2x3 sort) mean return 0.014 (1.4%), t 5.722; monthly data Jan 2010 to Dec 2024;… · LMH (low minus high P/B) mean return 0.003 (0.3%), t 0.845; same sample; no transaction costs stated.
OUR BACKTEST · Sharpe -0.03 · Return -1.8% · Max DD -19.0%
News may reveal systematic risk, but whether its context enhances the construction of systematic risk factors is still unclear.
PAPER REPORTS · Spherical ST + sparse-soft c-TF-IDF + multi-horizon IPCA, L=60: annualized OOS excess-return Sharpe 1.0334, Sep 2020 to… · Same raw spherical portfolio: annualized volatility 81.68%, maximum drawdown 62.23%; not risk-managed, not…
Option-implied factors are largely, but not entirely, spanned by the equity factor zoo. We construct 137 option-implied characteristics for optionable U.S.
PAPER REPORTS · bakshiKurt long-short factor (value-weighted decile, S&P 500 constituents, 30-day maturity): -11.23% annualized mean,… · ivs_convexity long-short factor: -14.78% annualized mean, vol 17.94%, Sharpe -0.82, MDD -96.94%, skew -3.59, t = -2.57;…
OUR BACKTEST · Sharpe -0.19 · Return -21.5% · Max DD -44.4%
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.
Abstract This research utilizes explainable artificial intelligence (XAI) techniques to explore the relationship between size-sorted environmental, social, and governance (ESG) portfolio indices (large-cap, mid-cap, and small-cap ESG portfolios) and their…
This study examines capital market reactions to the gazettal of Hong Kong's Stablecoin Ordinance. This event provides a clearly identifiable informational signal that resolves regulatory uncertainty.
PAPER REPORTS · Cumulative average abnormal return of 13.0% over the 2-day window (-1, 0), t = 8.230 (CAPM), event date May 30, 2025;… · Cumulative average abnormal return of 18.8%-18.9% over window (-1, +3), t = 7.661 (CAPM) / 7.697 (FF3); no transaction…
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%
We study exact-cardinality, equally weighted minimum-variance portfolio selection under a one-factor covariance model supplied in factor form. In the nonnegative homoskedastic regime, selecting the K smallest loadings is optimal.
OUR BACKTEST · Sharpe 0.65 · Return +50.5% · Max DD -24.3%
Abstract This paper investigates Magic: The Gathering (MTG) trading cards as a modern class of emotional assets and evaluates their role within diversified portfolios.
PAPER REPORTS · TCG Equal-Weighted Index, Oct 2010 - Mar 2025: annualized mean log return 18.73% (t = 5.48), volatility 13.01%, Sharpe… · TCG index alpha vs S&P 500: 17.84% annualized (t = 5.06), beta 0.07, R² = 0.01, same period, no cost adjustment stated
Abstract This paper investigates the pricing of ESG momentum in corporate bond markets, identifying a credibility barrier that conditions whether sustainability improvements are rewarded by investors.
PAPER REPORTS · Long-short ESG momentum quintile spread: mean 0.926 bps per month, t = 1.302, p = 0.196, Dec 2014 - Apr 2025 (114… · Conditional ESG momentum marginal effect of 0.877 bps per month (95% CI [0.292, 1.462]) for issuers excluded by 5+…
Signal correlation and PnL correlation are correlations over different index sets - across assets at each date versus across dates for scalar payoffs - and practitioners often treat the first as a proxy for the second.
OUR BACKTEST · Sharpe -0.83 · Return -17.6% · Max DD -18.1%
Abstract This research seeks to delve deeper into the financial significance of the eigenvector associated with the second-largest eigenvalue of the correlation matrix of returns.
OUR BACKTEST · Sharpe -0.48 · Return -35.9% · Max DD -49.7%
We build and evaluate a pre-game win-probability forecaster for individual maps (``games'') in professional \emph{League of Legends} (LoL).
PAPER REPORTS · Global time-based 0.2 holdout, n_te = 912, 2024-2026 corpus: proposed one-stage model RPS/Brier 0.2230, log-loss… · Per-game walk-forward, 4,605 scored games (min 500 prior games): proposed model RPS 0.2207; calibration intercept…
This study constructs a climate risk attention indicator for Chinese funds by applying Word2Vec-based text analysis to annual fund reports.
PAPER REPORTS · Carhart four-factor alpha regression coefficients (2013-2023, annual fund-year panel, fund and year fixed effects):… · Authors' summary claim: "an annualized alpha of approximately 2.7% associated with acute risk focus" (conclusion…
We propose a new model of expected stock returns that incorporates quantity information from market trading activities into the factor pricing framework.
PAPER REPORTS · Panel OOS predictive R2 (2010-2022, monthly individual stock returns, no demeaning): 0.75% single-factor CAPM BTQ;… · In-sample R2 (2000-2022 full sample): 1.01% single-factor MKT BTQ, 1.21% FF5C BTQ, vs 0.05% and 0.22% for beta-only
This paper examines whether the risk-adjusted performance of Environmental, Social, and Governance (ESG)-focused Exchange Traded Funds (ETFs) reflects distinct investment behavior or is primarily influenced by benchmark exposure, geography, and sector…
OUR BACKTEST · Sharpe 0.56 · Return +53.4% · Max DD -37.6%
Abstract We examine whether disproportionate insider control, or the divergence between insider voting and cash flow rights at dual-class firms, influences the extent to which stock price reflects information about future firm performance.
Recent advances in LLM agents enable a new paradigm for asset pricing, which we call Agentic Empirical Asset Pricing (AEAP): systems that autonomously conduct the scientific discovery process itself. We define AEAP and identify its core building blocks.
PAPER REPORTS · SEADS mean per-factor OOS Sharpe 0.25 on Panel A (JKP) and 0.16 on Panel B (CRSP/Compustat), OOS windows 2020\u20132025… · SEADS productivity 14.0 (Panel A) / 13.8 (Panel B) admissions out of a 300-candidate budget
The standard Fama-French three-factor model assumes constant factor loadings for the market, size, and value factors.
This paper provides robust empirical evidence that shocks to aggregate Research and Development (R&D) have persistent effects on macroeconomic dynamics and represent a significant risk for investors, as predicted by the ‘long-run risk’ literature.
PAPER REPORTS · Risk premium associated with effective R&D structural shocks: approximately 2% per year, estimated via Giglio and Xiu… · 4-year rolling-sum shock, 14 factors: premium 0.48, t = 3.28 (baseline specification)
Hedge ratios, factor models and diversified portfolios all rest on an estimate of which firms move together.
PAPER REPORTS · Variance-harvest attribution (selling variance at VIX-squared against the paper's 12m equal-weighted realized leg, July… · Risk by REC quartile over the same 329 months: probability of loss 0.29, 0.21, 0.26, 0.15; mean loss given loss…
OUR BACKTEST · Sharpe 0.73 · Return +68.2% · Max DD -36.5%
PAPER REPORTS · US single-country equity portfolios, static risk-minimizing FX exposure (lambda=0), 1990s-2023, in-sample, no… · US single-country equity portfolios, unhedged (full exposure), same period: Sharpe 32.13% (CAD), 45.92% (INR), 31.62%…
Asset-pricing models typically condition on a fixed information set. This paper endogenises the market's conditioning architecture by allowing portfolios to choose representations whose induced exposures affect prices.
Introduction In the context of global climate governance, corporate environmental performance is becoming critical for market competitiveness.
Investors interpret social disclosures from a risk perspective, yet relevant information can reach them through channels that differ sharply in regulatory enforcement and materiality: SEC filings, sustainability reports, or financial reports.
The authors present a rigorous empirical evaluation of three distinct optimization paradigms for institutional factor portfolio construction: an entropy-based photonic quantum annealer (Dirac-3, Quantum Computing Inc.), a commercial mixed-integer programming…
PAPER REPORTS · Dirac-3, best overall configuration (beta1=0, beta2=1): Sharpe 0.760, Sortino 0.841, Calmar 0.567, MDD -3.47%, CVaR5%… · Dirac-3 (beta1=0, beta2=0.5): Sharpe 0.721, Calmar 0.538, MDD -2.63% (lowest in both sweeps), CVaR5% -1.107%, annual…
OUR BACKTEST · Sharpe 0.25 · Return +11.4% · Max DD -18.7%
Shariah-compliant equity screening provides a transparent setting in which institutional rules determine who may own a stock.
PAPER REPORTS · SC Malaysia inclusions, 295 continuously listed liquidity-qualified events, Nov 2013-Nov 2025: matched… · 410 continuously listed inclusions (no turnover floor): +0.896pp [0,10] (p_date=0.127; p_wild=0.134) and +1.458pp…
In this paper we investigate the information content of the lower part of the spectrum of financial correlation matrices, as a source of information on market synchronization.
OUR BACKTEST · CAPITAL EXHAUSTED · FAILED SANITY CHECK
Current portfolio construction methods are either agnostic to the effects of idiosyncratic shocks (standard factor models) or to the latent data structure driving systematic returns (recent graph-based approaches).
PAPER REPORTS · Contagion Cut (proposed): CAGR 21.0%, Sharpe 1.07, Calmar 0.611, Jan 2019-Mar 2026, 0 bps transaction costs · Contagion Cut: Sharpe 1.04 at 10 bps, 1.01 at 20 bps, 0.929 at 50 bps (CAGR 20.5%, 19.9%, 18.3%), Jan 2019-Mar 2026
OUR BACKTEST · Sharpe 0.75 · Return +143.1% · Max DD -40.3%
This paper studies conditional allocation between a growth/technology ETF basket, denoted by $G$, and a defensive income/value-oriented ETF basket, denoted by $D$.
PAPER REPORTS · Selected smooth-score policy, 2017-06-28 to 2026-05-15, 10bp cost: 19.24% CAGR, 19.29% vol, Sharpe 1.01, Sortino 1.22,… · Selected policy vs 50/50 G/D: annual excess 1.78%, tracking error 3.74%, info ratio 0.48, max DD improvement 1.95%
OUR BACKTEST · Sharpe 0.92 · Return +111.2% · Max DD -31.6%
Factor structures are central to empirical work in economics and finance, and are usually used to model time-varying unobserved heterogeneity through interactive fixed effects (IFE).
I revisit the exchange rate disconnect puzzle, first documented by Meese and Rogoff (1983), using generative artificial intelligence (AI) to forecast currency returns based on economic fundamentals.
PAPER REPORTS · Annualized Sharpe ratio 0.594 at 48-month lookback (cross-sectional long top-2 / short bottom-2 of 9 currencies,… · Annualized Sharpe ratios 0.577 / 0.604 / 0.594 / 0.491 / 0.467 for 36 / 42 / 48 / 54 / 60-month lookbacks (2001-2024,…
When do outcome records carry enough signal to support reliable inferences about skill? When they do not, what should evaluators substitute? The framework answering the first question characterizes any decision domain with two parameters: the noise reflected…
The Observable Matrix Dynamics (OMD) approach monitors the time development of complex non-linear systems through the trajectory of a fixed-size distance matrix and its spectrum.
PAPER REPORTS · Early-warning ROC AUC (the paper's own signal, causal trailing 126-day features, label = forward peak-to-trough…
OUR BACKTEST · Sharpe 0.69 · Return +120.4% · Max DD -33.3%