Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
1,124 documents
The notebook presents the Almgren–Chriss framework for scheduling a large liquidation. It measures implementation shortfall against the arrival price and models two competing costs: market impact, which rises with trading intensity, and timing risk, which…
This case study explains how to construct forward-return labels for a cross-sectional foreign-exchange strategy that ranks currency pairs and buys or sells according to their relative ordering. It first maps four-hour spot bars into trading sessions using a…
The code computes standardized performance metrics from out-of-sample prediction tables, separately by fold and as headline aggregates. It supports regression and classification, including information coefficient, error measures, discrimination metrics, and…
This record captures one LangGraph forecasting run on whether the Federal Reserve would raise its target rate during 2026. Three agents produced probabilities, followed by a debate and a supervisor update. The logged outputs include an aggregate probability,…
This notebook uses double machine learning to test whether the association between the implied-minus-realized volatility spread and future equity returns persists after adjustment for observed confounders. It compares the adjusted estimate with naive…
This notebook assembles a research agent that searches for evidence and returns a structured probability for a binary question. It describes action parsing and validation, a turn budget, and a saved forecast artifact that records the rationale and supporting…
This notebook explains PCA as a feature-free latent-factor baseline for forecasting ETF returns. It decomposes each label’s training-window return matrix, using a loading for each fund and estimated factor premia to assemble forecasts. Because the same fund…
This notebook walks through a deployment cycle for a daily FX pairs model using Interactive Brokers as both the live data source and execution venue. It trains a Ridge regression model on a historical panel, computes a compact set of daily return, momentum,…
This notebook presents a neural stochastic discount factor model for a panel of CME futures. The model uses both product returns and observable characteristics, such as carry, momentum, and volatility, to construct latent factors and generate predictions for…
This utility describes a workflow for collecting public SEC 10-Q, 10-K, and 8-K filings and converting them into a common tabular dataset for downstream research. It applies form-specific text extraction: quarterly filings yield the management discussion…
This notebook explains feature construction from data beyond a single asset’s price history. It derives annualized futures roll yield from contemporaneous front and deferred contract prices, and uses three tenors to calculate normalized curve slope and…
This study re-prices leading ETF allocation and risk-control combinations across two cost grids while holding each registered strategy configuration fixed. One grid uses basis points per trade; the other uses per-share commission and half-spread, the…
This module describes two components in a multi-agent forecasting pipeline. A debate agent alternates between bullish and bearish arguments, requiring each side to address the other’s claims and provide a probability estimate with supporting evidence. It…
This notebook compares six long-only portfolio allocations for a multi-asset ETF universe. It uses Ledoit–Wolf covariance shrinkage to reduce the sampling variation that can destabilize optimization, and compares maximum Sharpe, minimum variance, risk…
This notebook shows how to use PCMCI to search for delayed relationships among ETF and volatility returns without specifying a causal graph in advance. It contrasts panel-based conditional-independence testing with pairwise Granger tests, which account for a…
This configuration defines a weekly futures research universe spanning equity indexes, government bonds, energy, metals, currencies, agriculture, and livestock. It sets Friday settlement as the decision snapshot and Monday open as the execution point. The…
This experiment examines how much a selected monthly US equity long-short signal depends on small-cap stocks. It applies a lagged market-equity filter that removes the smallest quartile from validation predictions, then reruns the same portfolio construction…
This notebook explains how PatchTST uses fixed-length patches of sequential market features to forecast NASDAQ-100 labels. Attention relates patches across a trailing hour while reducing the sequence length compared with attention over every minute. The…
This document explains a CME futures experiment using TabM, a parameter-efficient neural ensemble, on the same engineered feature rows and walk-forward folds used by linear and gradient-boosting models. TabM shares most weights across ensemble members to…
The document presents NLinear, a minimal sequence model for forecasting NASDAQ-100 stock returns from intraday features. It uses a fixed trailing window, subtracts the latest observation so the model works with changes rather than levels, and maps the…
This material explains how to evaluate a strategy chosen on validation data using predictions from a separate 2021 holdout. It keeps the selected allocation, concentration, risk controls, trading schedule, and costs fixed, changing only the predictions…
The document describes a pipeline for turning SEC 8-K filings into structured corporate events. A language model extracts event relationships, while explicit schema checks validate entity names, relation types, categories, and dates. Deterministic…
This module describes migrating a registry after a library changed the numbering of walk-forward folds while leaving their date windows and fitted values unchanged. Since fold identifiers appear throughout training specifications, prediction keys, input…
This notebook examines retained results from a real-strategy audit comparing the LEAN engine with matching ML4T Backtest profiles. It identifies the asset-class workloads supported by the frozen inputs and reports parity evidence across fills, valuations,…