Knowledge library

This notebook presents the Rademacher Anti-Serum (RAS) protocol as a way to adjust performance estimates for selecting from a finite class of strategies or signals. Empirical Rademacher complexity estimates how well the candidate performance matrix can align…

This notebook introduces NLinear as a baseline for predicting stock returns from ordered feature windows. Each example contains 60 consecutive sessions for one stock. For every feature, the model subtracts its latest value, maps the resulting history to a…

This notebook fits TabM neural models to an S&P 500 options short-straddle return target and compares three model capacities on the same feature panel used by linear and boosting approaches. TabM shares a neural backbone across ensemble members, while…

This notebook demonstrates deep hedging for a short European call. It simulates geometric Brownian motion paths, uses Black–Scholes delta hedging as a benchmark, and trains a semi-recurrent neural network to choose underlying positions that minimize a…

This document demonstrates Instrumented PCA, in which asset factor loadings are modeled as linear functions of characteristics observed before the return. It uses alternating least squares to estimate the characteristic-to-loading map and realized factors,…

This document describes a reproducible US equities benchmark drawn from the Chen, Pelger, and Zhu asset-pricing replication archive. It contains roughly 1.2 million monthly stock observations from 1967 through 2016, with 46 firm characteristics,…

This document explains how TSMixer processes a stock’s recent feature history as a sessions-by-features matrix. Its blocks mix information down feature columns across time, then across features within each session. Stacking blocks lets those operations…

This notebook compares zero-shot Chronos and TinyTimeMixer forecasts with an LSTM and a penalized linear model on an ETF panel. Every model receives the same univariate historical context, but the pretrained models forecast that context series rather than…

This notebook estimates whether a crypto perpetuals premium z-score is associated with subsequent eight-hour returns under an intervention, adjusting for price volatility, funding rate, and the premium’s deviation from its recent mean. Double machine…

This notebook evaluates whether option-market measures can rank future returns across stocks. It fits declared linear models on option-derived features, using walk-forward validation, and compares penalty strengths for ridge, lasso, and elastic net. The…

This study asks whether option-market quantities can rank future stock returns. Its features include implied volatility across maturities, put-call skew, term-structure slope, and the variance risk premium. Because many measures are represented in several…

This notebook adapts an adversarial stochastic discount factor design to daily U.S. equities. A portfolio-weight network forms a factor from next-day excess returns, while a competing moment network helps train the pricing kernel; a separate beta network…

This notebook turns a real supply-chain knowledge graph and institutional 13F holdings into machine-learning features. It derives network measures such as centrality and dependency indicators, estimates supplier concentration and competitive exposure, and…

This notebook demonstrates an operational cycle for an ETF prediction strategy: refresh market data, recompute financial features, retrain a Ridge model, save deployment artifacts, generate current cross-sectional predictions, replay the predictions through…

This notebook compares LightGBM with a minimal multilayer perceptron, TabM, and optionally TabPFN for cross-sectional ETF return prediction. Models are evaluated on shared walk-forward folds using rank information coefficient, with chronological validation…

This notebook compares a Random Forest with XGBoost, LightGBM, and CatBoost on a panel of anonymized firm characteristics and returns. The dataset supplies temporal training, validation, and test splits. Models are evaluated using Spearman rank information…

This notebook describes how to produce holdout predictions for a selected crypto perpetuals funding strategy. It resolves the configuration from validation results, carries its checkpoint choice forward, and builds a new training specification using data…

This notebook presents a cross-case-study inventory of engineered financial features and the strongest registry information coefficient for each market study. It counts features and feature-name families, compares feature-space sizes, and summarizes…

The document explains how to identify market regimes by dividing returns into overlapping windows and treating each window as an empirical distribution. It measures the distance between windows through matched, sorted quantiles, so differences across the…

This notebook presents a conditional autoencoder that preserves the structure of an instrumented latent factor model while replacing the linear map from firm characteristics to factor exposures with a neural network. Monthly returns are represented as…

This case study fits regularized linear models to returns from short at-the-money straddles held to expiry. Because premium income caps the gain while losses can grow without bound, a few severe losses dominate a squared-error regression objective. The…

This notebook compares two locally run, open-weight embedding models on a retrieval task using passages from recent 10-K filings for a small set of large US companies. Both models receive the same two-sentence passages and a fixed set of queries spanning…

This document fits TabM, a weight-sharing neural ensemble, to option-derived features for predicting forward equity returns and risk-adjusted returns. Its members use one shared two-layer network, with separate activation scaling and output heads, then…

This document presents a structured state record for research agents, separate from their conversation transcript. The record stores the question and cutoff, gathered evidence, unresolved questions, tool-call history, gate outcomes, and synthesis status.…