Knowledge library

The document describes a specialized backtest for a weekly S&P 500 options strategy. Each cohort selects highly ranked constituents, sells near-the-money call and put options with roughly a month to expiration, and delta-hedges with shares when net delta…

The document presents GReaT, a framework that serializes rows of mixed numerical and categorical financial data as text, fine-tunes a language model on those records, and parses generated text back into tables. Its example builds ETF features from historical…

The document explains how uncertainty from a model can provide information beyond its point estimate. It contrasts GARCH, which defines volatility from past returns, with a stochastic volatility model that treats volatility as a latent autoregressive process…

This cross-case analysis examines how predictive information, measured by information coefficient (IC), translates into portfolio Sharpe across nine trading case studies. Its central point is that implementation mediates the relationship: entry rules,…

This notebook uses principal component analysis to represent the common movements in a broad US equities panel. PCA extracts directions that explain shared variation in returns; each stock’s loading measures its exposure to each direction. A prediction…

This notebook evaluates security rules for a document-grounded financial assistant using six hand-built cases. The cases cover prompt injection, fabricated figures in untrusted material, attempted actions, and citations to content that was not retrieved. Two…

This notebook refits the FX configuration already selected by validation and registers its predictions for a later holdout backtest. It resolves the selection from solvent validation backtests, constrained to a frozen candidate set, then rebuilds the…

This notebook presents a temporal convolutional network (TCN) for predicting ETF forward returns from sequences of trailing return features. Causal convolutions ensure an output uses only observations up to its date, while exponentially increasing dilation…

This notebook explains tick and volume imbalance bars, then compares adaptive, fixed threshold, and rolling window approaches on NVDA trade data. Tick imbalance accumulates signed trade directions until a threshold is reached; the expected threshold depends…

This case study compares alternative position sizing methods for CME futures against an equal weight baseline. It explains how inverse volatility sizing uses each contract’s own volatility, while covariance based methods also account for relationships…

This notebook explains how to build a continuous futures price history from individual expiring contracts. It identifies front-month contracts using trading volume, applies a no-rollback constraint to avoid spurious switches, and compares calendar-based roll…

This notebook explains how to turn fitted GJR-GARCH and hidden Markov models into trading features while controlling look-ahead bias. GJR-GARCH estimates conditional volatility and captures the greater impact of negative return shocks; a two-state Gaussian…

This notebook surveys methods for finding changes in the process that generates a financial series, using daily SPY data as its example. It contrasts the Zivot–Andrews test, which estimates one break while testing for a unit root, with multiple-break…

This notebook turns currency-pair prediction rankings into a traded baseline. At each decision time, it forms equal-sized long and short sleeves from the highest- and lowest-ranked pairs, then evaluates them with an FX backtest engine. Equal weighting is…

This utility prepares prediction artifacts for live-demo notebooks by normalizing differing column names and date formats into a common timestamp, asset, and prediction structure. It groups duplicate timestamp-asset observations and averages their scores.…

This proof script exercises a reduced CME futures research workflow from model predictions through portfolio weights and backtesting. It checks that predictions cover exactly the expected product, timestamp, and fold keys, that fitted states and prediction…

This notebook compares two Transformer designs for forecasting 21-day ETF returns from trailing momentum features. PatchTST groups consecutive days into patches, placing short sequences of local shape in each token. iTransformer instead treats each feature’s…

This notebook trains a Skip-gram Word2Vec model on a small, sentiment-labeled financial news corpus and examines what its nearest neighbors reveal. The method represents words based on the contexts in which they appear. In the example, profit and loss become…

This notebook sets out a descriptive way to translate gross returns into net performance by modeling trading frictions, financing, and fund expenses separately. Its parameterized cost stack calculates trading costs from turnover and trade size, financing…

This document describes a workflow for collecting FRED Treasury yields and economic indicators, aligning series with different reporting frequencies to a daily calendar, and loading or filtering the resulting dataset. The indicators include Treasury rates…

This module describes a search interface for research agents, with a live provider and a deterministic mock provider. Searches can limit result counts and apply a publication-date cutoff, supporting point-in-time research by removing results dated on or…

This module defines a differentiable objective for end-to-end portfolio learning. It turns bounded asset-level risk weights into portfolio exposures using volatility scaling, computes average gross returns over available assets, and optionally subtracts…

This notebook analyzes reconstructed NASDAQ order books to describe intraday spreads and depth at the best bid and ask, then examines whether order flow imbalance is associated with the next bucket’s return. It expresses spreads in basis points to make costs…

This notebook explains how a conditional autoencoder extends instrumented PCA for ETF return modeling. Both methods map fund features to factor exposures and combine those exposures with factor returns; the autoencoder replaces IPCA’s linear…