Reviews of published findings and implementation questions. These reviews do not imply a completed house replication.
Curated by Signal & Evidence. Read our research approach for how we distinguish author findings from house tests.
Every discarded feature and revised question is part of the research history. The Axiomatic Trader brings that history into the decision.
Study: The Axiomatic Trader: Latent Regularity, Information Budgets, and the Canonical Form of a Quantitative Investment System
A dependence graph constrains which company characteristics interact inside a neural model.
Study: Dependence-Informed Sparse Neural Architecture for Stock Return Prediction
A study of earnings surprises asks whether company news crowds out the market news arriving alongside it.
Study: Firm–specific information processing and the delayed discovery of macroeconomic news: evidence from earnings announcement returns
A richer volatility-surface model follows more than the level of the smile. The improvement depends on what is being measured.
Study: Beyond the Skew-Stickiness Ratio: Transport Geometry of Spot-Driven Variance Surface Dynamics
A reconfiguration index follows which groups of stocks move together, rather than only how much the market moves.
Study: The Reconfiguration Premium: Co-movement Structure as an Unspanned Dimension of the Variance Risk Premium
Entropy penalties aim to restrain unstable weights. The question is what the tracker gives up—or gains—in the process.
Study: An Entropic Factor Model for Robust Portfolio Replication
A connected-market model follows rebalancing pressure beyond the fund’s own underlying asset.
Study: The Loop-Gain Matrix: Coupled Rebalancing Feedback and the Blind Spots of Scalar Stability Monitoring
The MINGLE study groups stocks by the forces they respond to, then uses that map in portfolio construction.
Study: Beyond Co-Movement: Locality by Exposures Enables a Joint Factor-Graph Framework for Portfolio Diversification
Correlation distance, return ranks and volatility ranks form a compact market representation. The trading rule is part of the story.
Study: Are Three Matrices All You Need To Beat the Market? Observable Matrix Dynamics for Portfolio Optimization
A compact neural risk model targets the compounding penalty from volatility. The portfolio consequences deserve a closer look.
Study: Neural Network-Driven Volatility Drag Mitigation under Aggressive Leverage
The futures curve contains more than its front-month slope. A white paper uses the ordering of contracts to change equity and volatility exposure.
Study: The Squid Programs: Trading the VIX Curve. Dynamic volatility using the VIX term structure.
A neural estimator uses unequal stock histories without discarding the longer records. The authors report a sizeable risk difference.
Study: End-to-End Neural Shrinkage of Indefinite Pairwise Correlation Matrices for Small-Cap-Inclusive Portfolios
A framework tested across 84 futures contracts separates the shape of the payoff from the market behavior behind it.
Study: The Science and Practice of Trend-Following Systems
A sudden crash and a grinding bear market create different demands on protection. This paper puts puts and trend in one framework.
Study: Tail Risk Management with Puts and Trend Following: A CVaR Framework for Crashes and Drawdowns
KellyBoost skips the forecast-then-optimize sequence and trains directly on wealth growth. The objective changes the bet.
Study: KellyBoost: Growth-Optimal Portfolio Construction with Gradient-Boosted Trees
A Norwegian register study looks beyond the most visible executives. Which part of its information can an outside investor actually observe?
Study: Flying Below the Radar: Insider Trading by Executives Below the Top
