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 · 28 shown
Accurate prediction of stock price movements is of substantial importance to investors, portfolio managers, and financial regulators, and although machine learning models are increasingly deployed in quantitative finance, the limited transparency of many such…
PAPER REPORTS · XGBoost long/flat, hold-out period, as-is configuration: annualized return −11.59%, Sharpe −0.241 at 10 bps one-way… · XGBoost long/short, hold-out period, as-is configuration: annualized return −34.29%, Sharpe −1.014 at 10 bps one-way…
OUR BACKTEST · Sharpe 0.09 · Return +2.4% · Max DD -14.9%
Language models that read financial news are usually trained on text from the same years used to test them, so a backtest can reward hindsight.
PAPER REPORTS · Monthly, price+text combination across all readers and models, 63-day shocks, test 2022–2024, net of 10bp per dollar… · Same monthly buffered portfolio: net return 12.4%/yr, volatility 10.4%, max drawdown 8%, turnover 60% per month,…
OUR BACKTEST · Sharpe -0.73 · Return -19.9% · Max DD -34.5%
Formulaic alpha mining seeks to discover executable expressions that capture predictive market signals in a vast, noisy search space.
PAPER REPORTS · AlphaRLM-8B CSI 300: annualized excess return 12.14% (0.1214±0.0011), MDD -6.15%, IC 0.0256, RankIC 0.0424, ICIR… · AlphaRLM-8B CSI 1000 (CSI 300-trained factor pool): annualized excess return 17.45%, MDD -11.98%, IC 0.0302, RankIC…
OUR BACKTEST · Sharpe 0.83 · Return +105.8% · Max DD -50.8%
Wavelet-based financial forecasters typically use the transform only to denoise, or reduce it to a single spectral snapshot at the forecast origin, and the convolution that produces the coefficients is usually bilateral, so it can read past the forecast…
PAPER REPORTS · S&P 500 DSTNet asymmetric risk-off allocation, test 2023-06-01 to 2024-05-31, 10 bps per unit turnover, idealised… · NYSE DSTNet risk-off, same period, 10 bps: Sharpe 1.80, MaxDD 5.65%, CumRet 11.31%, exposure 56.77%, total turnover…
OUR BACKTEST · Sharpe 0.46 · Return +21.1% · Max DD -24.7%
We develop a price-based framework for stochastic portfolio theory in which trading strategies are generated from nominal price weights and evaluated relative to a price-weighted benchmark.
PAPER REPORTS · Cap-based p-diversity-weighted portfolios, terminal log relative wealth vs cap-weighted index on U^S (2002–2021,… · Cap-based p-diversity-weighted portfolios, terminal log relative wealth vs cap-weighted index on U^P (2002–2021, no…
OUR BACKTEST · Sharpe 0.38 · Return +39.6% · Max DD -47.5%
The enhanced index tracking (EIT) portfolio selection problem aims to construct a portfolio that is expected to outperform a benchmark index.
PAPER REPORTS · M-ER, known mean/covariance, short selling allowed, OOS Jan 2020-Dec 2024, monthly rebalancing, transaction costs not… · M-TSV, known mean/covariance, short selling allowed, same period, costs not stated: mean return 0.048939, SD 0.150532,…
OUR BACKTEST · Sharpe 0.70 · Return +62.4% · Max DD -32.5%
Abstract The fact that the solution of the Markowitz model is numerically unstable is recognized as one of the principal reasons for its poor out-of-sample results when applied in practice.
PAPER REPORTS · Out-of-sample Sharpe ratio of the μp=β (δ-stable) portfolio, daily data 2000–2020, rolling window, net of 10 bp ×… · Same setup, DAX: 0.0099 (w=120), 0.013 (w=180), 0.0206 (w=240), 0.0312 (w=480).
OUR BACKTEST · Sharpe 0.66 · Return +49.0% · Max DD -31.1%
Reinforcement learning for trading often struggles to balance upside participation with drawdown control.
PAPER REPORTS · SPY, test 2020–2022, seed 42, 0.1% proportional transaction cost: total return 27.62%, annualized return 8.48%, Sharpe… · SPY, test 2020–2022, mean ± std over seeds {7,11,19,23,42}, 0.1% cost: total return 0.2725 ± 0.0109, Sharpe 0.6219 ±…
OUR BACKTEST · Sharpe 0.89 · Return +42.3% · Max DD -15.6%
This paper examines whether a cointegration-based pairs trading strategy between PepsiCo and The Coca-Cola Company is statistically robust and economically exploitable.
PAPER REPORTS · In-sample 2018–2023, θ*=(2.15, 0.50): annualised net Sharpe 0.67, net P&L $16,941 on $100,000, 9 round-trips. · In-sample 2018–2023 excluding the COVID window: annualised net Sharpe 0.28, net P&L $5,759, 8 trades (0.20% costs).
OUR BACKTEST · Sharpe 0.11 · Return +0.2% · Max DD -1.4%
Predicting stock price movements is highly challenging due to the noisy, nonlinear, and multi-factor nature of financial markets.
OUR BACKTEST · Sharpe 0.70 · Return +20.9% · Max DD -6.5%
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%
Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), channel-indiscriminate multi-scale decomposition that conflates heterogeneous frequency signatures, and static…
PAPER REPORTS · WaVeFuse directional strategy, 365-day 2023 out-of-sample, 10bp per-trade cost: mean CAGR 24.6%, mean Sharpe 3.69, mean… · Per-index directional (2023, 10bp): KOSPI CAGR 34.4%, Sharpe 4.73 [95% CI 4.37-5.09], max DD 1.9%; GDAXI 13.3%, Sharpe…
OUR BACKTEST · Sharpe 0.03 · Return +2.7% · Max DD -41.1%
MASTER's inter-stock multi-head attention -- the module responsible for modeling cross-sectional stock relationships -- accounts for 42.5% of model parameters and 25% of predictive value.
PAPER REPORTS · Long-short portfolio Sharpe at N~3,500 (full A-share, test 2019-2020, 4 seeds, frictionless): PureLSTM 5.6 +/- 0.5;… · IC / Rank IC as the primary reported performance: CSI300 Original 0.058 +/- 0.007 / 0.066 +/- 0.003 (5 seeds); CSI800…
OUR BACKTEST · Sharpe -0.58 · Return -50.8% · Max DD -63.3%
Frequent market instability and the lack of rigorously validated forecasting frameworks pose significant challenges for predicting market stress in the Dhaka Stock Exchange (DSE).
PAPER REPORTS · Random Forest crash-gated risk-off strategy, pooled equal-weighted, 2019-2022 test period: total return 67.26% (15.01%… · Annualized volatility 16.39% (strategy) vs. 18.11% (buy-and-hold); maximum drawdown -32.21% vs.
OUR BACKTEST · Sharpe 0.47 · Return +25.2% · Max DD -21.6%
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%
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%
Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific investment preferences.
PAPER REPORTS · Weekly rebalanced equal-weight long-only top-100 portfolio from Qwen3-8B scores, 427 S&P 500 stocks, 29 signal weeks /… · Realized Sharpe of the top-100 portfolios is shown only graphically (Figure 5c, axis range roughly 2–4); no point…
OUR BACKTEST · Sharpe 0.52 · Return +57.3% · Max DD -40.6%
We develop parametric Entropic Value-at-Risk (EVaR) portfolio optimization for tempered stable Lévy returns.
PAPER REPORTS · ICA+NTS minimum-EVaR (EVaR_95): gross annualized Sharpe 0.616, CAGR 8.60%, annualized vol 15.28%, cumulative return… · ICA+NTS minimum-EVaR net Sharpe: 0.608 at 5bp, 0.599 at 10bp, 0.573 at 25bp; net cumulative return 630.95% at 25bp
OUR BACKTEST · Sharpe 0.24 · Return +20.5% · Max DD -37.6%
We present in this article a non-parametric value-at-risk (VaR+CVaR) algorithm that remains accurate for an arbitrarily large number of underlying positions. The algorithm solves the two inherent problems of VaR estimation.
PAPER REPORTS · Median 99% daily VaR breach rate 1.0 +/- 0.1% across 9 parameter settings, 500 random portfolios, no transaction costs… · Per-configuration medians (no added delay): 0.97%, 1.06%, 1.09% (1260-day window, 14/30/45-day vol); 0.90%, 0.99%,…
OUR BACKTEST · Sharpe 1.58 · Return +17.6% · Max DD -3.4%
We develop a geometric theory of arbitrage-free implied variance surface dynamics.
PAPER REPORTS · Out-of-sample RMSE(delta a2) improvement of full (beta,eta,psi) model over SSR-only: 17-21% at 3M-6M (215.7 vs 272.8 at… · Out-of-sample RMSE(delta a1) improvement of adding eta: 1-4% versus SSR-only at 1M-6M, essentially flat at 12M
OUR BACKTEST · Sharpe -0.84 · Return -0.1% · Max DD -0.1%
Financial forecasting models are typically developed in full precision, yet production deployment often requires low-precision inference to reduce memory and computational cost. Post-training quantization (PTQ) enables such deployment without retraining.
PAPER REPORTS · FP32 mean daily IC (cross-sectional Spearman, averaged over test dates, 2018-2025 walk-forward): TSMixer 0.490±0.043,… · Baseline mean daily IC over the same folds: pooled HAR 0.408, persistence (trailing 5-day realized vol) 0.315
OUR BACKTEST · Sharpe 0.41 · Return +41.7% · Max DD -37.2%
Specialist training beats generalist scale when forecasting financial statements. To our knowledge, no prior work jointly forecasts complete financial statements beyond one year, yet in a discounted-cash-flow valuation most firm value sits past that window.
PAPER REPORTS · Forma change-space R^2 0.289 on full test sample, test period 2010-2024, no transaction costs applicable (forecasting… · Forma per-horizon R^2: 39.0% at h=1 falling to 22.5% at h=20 (full sample); 38.0% at h=1 to 23.7% at h=20 (LLM sample)
OUR BACKTEST · Sharpe 0.57 · Return +17.5% · Max DD -10.5%
Predicting financial asset returns remains one of the most difficult challenges in empirical finance, driven by the low signal-to-noise ratio and the semi-strong form of market efficiency.
PAPER REPORTS · Sector LSTM (main 3-layer, k=10, 1995-2024): mean daily long-short return 0.100% before costs, Newey-West t = 7.81,… · Sector LSTM appendix figures (after 2bp per half turn): mean daily return 0.053%, t-statistic 4.106, annualized return…
OUR BACKTEST · Sharpe -0.03 · Return -9.6% · Max DD -140.3%
Risk-aware Q-learning (RaQL) provides a model-free, two-timescale estimator for dynamic risk objectives, but its finite-budget behavior remains fragile: fixed inner-loop hyperparameters can produce unstable value estimates, persistent Bellman residuals, and…
PAPER REPORTS · Scheme 6 out-of-sample (918 daily obs, chronological test set, after 5bp turnover costs, mean over 20 seeds): Sharpe… · Scheme 0 fixed-parameter baseline out-of-sample (same test set, after 5bp costs, 20 seeds): Sharpe 0.5628 (sd 0.2281),…
OUR BACKTEST · Sharpe 0.34 · Return +16.6% · Max DD -10.4%
Conformal prediction has traditionally been used to quantify prediction uncertainty.
PAPER REPORTS · DEV 2016-2021 (1,511 days), Config A: 28.45% annualised net log growth, Sharpe 1.336, max drawdown 27.68%, Calmar… · DEV 2016-2021, Config B: 25.84% annualised net log growth, Sharpe 1.386, max drawdown 20.26%, Calmar 1.376, annualised…
OUR BACKTEST · Sharpe 0.41 · Return +45.1% · Max DD -40.4%
Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs).
PAPER REPORTS · FinSMART (static): cumulative return 264.9%, annualized return 91.5%, Sharpe 1.97, Sortino 2.40, Calmar 4.23, RankIC… · FinSMART (periodically retrained every 6 months): cumulative return 406.2%, annualized return 125.7%, Sharpe 2.41,…
OUR BACKTEST · Sharpe -0.46 · Return -48.2% · Max DD -75.2%
We audit whether candle-based machine-learning models can turn predictions of cryptocurrency extrema or short-horizon outcomes into positive Binance Spot paper policies after assumed costs.
PAPER REPORTS · Frozen mandatory-daily selector: -6.72% compounded, 2026-07-01 to 07-19, 19 cycles, 3 wins/16 losses, 31 bps… · Frozen mandatory-daily selector cost stress, same period: -4.74% at 20 bps, -6.72% at 31 bps, -10.21% at 51 bps…
OUR BACKTEST · Sharpe 0.00 · Return +0.0% · Max DD 0.0%
The distribution of a normal mean-variance mixture depends on the law of its positive mixing variable. We compare six parametric mixing laws with a grid nonparametric maximum likelihood estimator under the same determinant identification constraint.
PAPER REPORTS · Model-based lower-envelope CPT value at the robust optimum: -0.04478 at 5% annual reference return; -0.09245 at 10%… · Empirical holdout CPT value at the robust weights: -0.04867 at 5% reference; -0.10049 at 10% reference (holdout 483…
OUR BACKTEST · Sharpe 0.13 · Return +0.1% · Max DD -0.2%