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.
715 documents
This notebook uses NASDAQ ITCH-derived trade records to examine intraday trading activity. It resamples individual trades into time bars and compares share volume, trade counts, last prices and volume-weighted prices for one ticker selected from each of…
This notebook explains how market impact grows with order size and uses the square-root participation model to frame strategy capacity. It distinguishes inputs available from market data, such as volatility and average daily volume, from the impact…
This notebook examines how return forecasts for ETFs can express uncertainty, comparing Monte Carlo dropout with deep ensembles. Dropout remains active across repeated inference passes, while an ensemble measures disagreement among separately trained…
This notebook gathers registered double machine learning estimates from multiple trading case studies and compares their uncertainty and diagnostics. It loads current rows from each study’s registry, checks registry integrity and label uniqueness, makes…
This notebook fits a declared LSTM model for forecasting in an S&P 500 options study. The network receives chronological windows of each symbol’s history and uses gated recurrent state to represent information across sessions, rather than relying only on…
This notebook compares three ways to classify financial-news sentences as positive, neutral, or negative: TF-IDF word and phrase features with logistic regression, averaged static word vectors with a classifier, and a pretrained FinBERT sentiment model.…
This notebook explains how to build and inspect a quarterly equity fundamentals panel from SEC XBRL data. Each observation carries both the fiscal period it describes and the filing date when the information became public. That distinction is essential in…
This notebook evaluates accounting and price-based characteristics as standalone predictors of next-month US stock returns. It computes monthly cross-sectional rank correlations between each characteristic and the return label, then summarizes them across…
This notebook screens candidate features for a CME futures case study against forward returns. For each feature, it computes cross-sectional rank correlations between feature values and subsequent returns, summarizes the correlation over dates, adjusts…
This notebook clusters monthly macroeconomic indicators to describe market conditions independently of equity returns. It aligns FRED series to month-end observations, standardizes unemployment, the federal funds rate, the yield-curve spread, and…
This notebook adapts Diffusion-TS to generate synthetic daily ETF return sequences. Its denoiser predicts the original series and decomposes that prediction into a polynomial trend, selected Fourier components, and a residual. A combined time-domain and…
This notebook builds a monitoring workflow for a deployed financial model using real holdout artifacts. It checks that incoming feature data is populated and structurally valid before measuring drift, then compares reference and current windows. Feature…
This notebook explains how to interpret Ridge regression forecasts for an ETF panel with SHAP. For a linear model, each feature’s attribution is its coefficient times the feature’s deviation from its training-background mean, so the attributions can be…
This notebook compares two methods for estimating bid-ask spreads when historical data contains daily open, high, low, close, and volume but no quotes. Corwin-Schultz separates spread from volatility by comparing daily and two-day high-low ranges, relying on…
This notebook presents a workflow for turning SEC annual and quarterly filings into structured text suitable for later sentiment, topic, and embedding analysis. It maps desired sections to form-specific item numbers, emphasizing that management discussion…
This notebook explains how a conditional autoencoder extends an instrumented principal component model: a neural network maps stock characteristics to factor exposures, while the model retains the same exposure-times-factor-return structure. It fits the…
This study screens financial and GJR-GARCH volatility features against forward equity returns. For each session, it calculates the rank correlation across stocks between a feature and subsequent returns, then assesses average association, consistency across…
This reference describes two financial news corpora used for sentiment analysis, text-feature development, and experiments linking news to returns. FNSPID connects headlines with stock tickers and covers a broad historical span; a smaller sample is available…
The document derives European call and put prices under Black-Scholes, checks their relationship through put-call parity, and computes implied volatility by numerically solving for the volatility that matches an observed option price. It also defines Delta,…
This module defines how a holdout selection field is assembled across validation stages and strategy labels. It addresses discrepancies that can make frozen candidate sets and live reconstruction select different configurations, or cause later analysis to…
This notebook shows how to test whether four managed-portfolio strategies add explanatory power for SPY returns after controlling for broad movements captured by ten principal components. The candidate portfolios rank ETFs by recent momentum, low volatility,…
This document describes a workflow for turning quarterly SEC 13F bulk filings into an institutional holdings panel. It selects the latest filing per manager by filing date, uses CUSIP rather than filer-entered company names to identify securities, and…
The document explains instrumented principal component analysis for modeling ETF returns. Unlike ordinary PCA, which assigns each fund fixed factor exposures, IPCA makes each fund’s exposures a shared linear function of its observable features. It estimates…
This notebook uses NASDAQ ITCH trade records to examine how volume and trading activity vary through the regular session. It resamples trades into time bars, compares price and volume for representative high-, medium-, and low-activity stocks, then…