Knowledge library

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 notebook uses real ETF data to assess whether a momentum signal remains useful under reasonable changes to its lookback, market regime, and implementation. It computes cross-sectional information coefficients between momentum and forward returns, then…

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 notebook constructs four model-based features for S&P 500 option research: next-day volatility forecasts from GJR-GARCH and stochastic volatility, plus the differences between each forecast and the option market’s implied volatility. It explains how the…

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.…

This notebook examines linear-model regularization for predicting returns across currency pairs. It distinguishes collinearity among input features from dependence among the assets: currency pairs share underlying currencies, so their returns and rankings…

This configuration note explains the choice of the saga solver and a tighter convergence tolerance for L1 logistic regression on three-class labels. It contrasts saga with liblinear, citing runtime measurements on a Nasdaq microstructure panel and reported…

This module describes checks for whether prediction and backtest inputs cover the sessions and folds specified by a study. Relative checks compare candidate models with one another, so they can miss a shared failure: stale fold boundaries or an upstream join…

This notebook distinguishes predicting returns from claiming that momentum causes them. It treats a stock’s prior-year return, excluding the latest month, as the treatment and forward return as the outcome. Recent volatility, illiquidity rank, and volume…

This notebook aggregates LightGBM results across multiple trading case studies and compares them with linear and TabM baselines. It examines the highest-IC configuration for each case study, reports heteroskedasticity-and-autocorrelation-consistent…

This utility describes a diagnostic workflow for data artifacts produced by quantitative research pipelines. It profiles numeric columns for nulls, non-finite values, zeros, distinct values, quantiles, and tail behavior, then flags columns that cross…

This notebook compares ways to measure volatility and develops heterogeneous autoregressive (HAR) volatility models alongside roughness analysis. It uses intraday returns to estimate session realized variance, distinguishes intraday movement from overnight…

The notebook builds prediction intervals around gradient boosting forecasts with split conformal prediction. It fits a model on an earlier training segment, measures absolute residuals on a later calibration segment, and uses a finite-sample order statistic…

This notebook compares four reference ETF allocations using historical crisis windows, hand-authored simultaneous asset shocks, Student-t Monte Carlo simulations, and market-regime statistics. It explains a maximum drawdown measure and uses daily…

This notebook compares CSV, Parquet, Feather, and HDF5 storage using a deterministic one-million-row OHLCV panel. It measures write time, materialized read time, file size, and reads that select only two columns. The timing policy uses a single write…

This notebook presents a pipeline for turning financial headlines into stock-level signals. It cleans and standardizes a news corpus, removes exact and prefix-matched duplicates within ticker-date groups, and uses sentence embeddings to represent headline…

This notebook explains a market data lifecycle for daily OHLCV data: load an initial history, fetch a small overlapping delta, detect missing sessions, and summarize each symbol’s freshness and validation issues. It describes why the update window should…

This notebook builds a forecasting agent that alternates between web searches and probability forecasts. A small two-method language-model interface lets the same loop use a mock, local, or commercial provider. The agent receives a prediction-market question…

This notebook examines information-driven sampling by constructing tick and volume imbalance bars from trade data. It verifies a manual tick-imbalance implementation against a library sampler, then sweeps expected bar sizes and adaptation settings to compare…

This analysis compares risk overlays across case studies by loading their overlay backtests from a registry and measuring Sharpe and maximum drawdown against an allocation-stage baseline, with a signal-stage fallback. It classifies configurations into rule…

This notebook develops Black-Scholes pricing for European calls and puts, checks put-call parity, and computes implied volatility with Brent root-finding. It also defines Delta, Gamma, Vega, Theta, and Rho and uses plots to illustrate how option…

This notebook describes a patched transformer for sequence prediction in an S&P 500 equity and options study. It divides a time window into contiguous blocks and represents each block as a token, allowing attention to compare distant parts of the window…

This notebook explains instrumented principal component analysis (IPCA) for a changing US equities panel. Traditional PCA assigns each stock a fitted loading, which cannot naturally cover names absent from the training sample and stays fixed as a company's…