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
This notebook tests how sensitive an ETF momentum backtest is to its assumed trading fee. It holds the strategy’s weights and trading schedule fixed, reruns the simulator across a range of per-leg costs, and compares growth, Sharpe ratio, and drawdown. It…
The notebook estimates how much an equal-weight portfolio of surviving US equities can overstate returns relative to the full starting universe. It first examines when the panel records symbols leaving, finding that recorded exits begin only in the final…
This notebook presents a multi-round bull-versus-bear debate for a contested probability forecast. Each side argues from shared research-agent summaries, sees the other side's prior position, and revises its probability. The process stops when the forecast…
This exploratory analysis introduces option contracts and chain structure, then profiles a 2020 sample of S&P 500 options across eight underlyings. It explains moneyness, intrinsic and time value, implied volatility, Greeks, and how strike, expiration, and…
This analysis reads a registered backtest pipeline for a monthly US equity strategy based on firm characteristics. It reports Sharpe uncertainty, probability and deflated Sharpe measures, paired strategy comparisons, holdout decay, and a cost analysis…
This notebook evaluates position-level stop losses, trailing stops, and time exits on the allocation lineage that ranks highest by validation Sharpe among eligible full-coverage candidates. Each overlay is compared with its own no-overlay parent, isolating…
This notebook builds fitted-model features from foreign-exchange price histories, complementing indicators calculated directly from past prices. It describes three approaches: a state-space filter that estimates a slowly changing price level and related…
This notebook compares portfolio weighting rules for an S&P 500 options strategy that sells straddles. It holds the selected symbols and other strategy settings fixed while replacing the equal-weight baseline with allocators that use either model predictions…
This notebook measures how execution costs affect the already selected crypto perpetuals configuration. It holds the model, checkpoint, entry rule, allocator, and risk control fixed, then reruns the strategy across a declared grid of round-trip charges on…
This notebook describes a workflow for turning S&P 500 companies’ quarterly MD&A disclosures into trading features. It uses filing acceptance dates as the point-in-time anchor, collapses multiple filings for a company on the same date to the latest period,…
This chapter surveys deep learning for time series through a practical question: when does observation order contain information that cross-sectional prediction misses, and which model designs can use it? It covers recurrent networks and their sequential…
This read-only analysis brings validation predictions from several model families together to assess whether they are complete, how well they rank stocks, whether ranking skill persists across folds, and whether apparently similar models contribute distinct…
This notebook applies TabM, a tabular neural architecture that shares a two-layer feature network across ensemble members. Each member scales the shared representation with its own learned vector and uses its own output layer; averaging member predictions…
This notebook explains risk-premium PCA, which modifies the return covariance matrix by adding a weighted outer product of the training-period mean returns. Its leading eigenvectors define static factor portfolios; raising the weight tilts the factors toward…
This notebook uses SHAP to explain Ridge regression forecasts of ETF returns. For a linear model, feature attributions have a closed-form relationship to the fitted coefficients and deviations from background feature values, allowing the analysis to check…
This notebook explains Kalman filtering as a way to extract features from financial prices. A local linear trend state tracks both a latent price level and its slope, while an observation model accounts for noisy closes. Each update produces a filtered…
This notebook presents instrumented principal component analysis (IPCA), a latent-factor approach to forecasting returns from firm characteristics. Instead of assigning each characteristic a direct return weight, IPCA models each firm’s factor exposures as a…
This notebook describes producing an out-of-sample prediction set for a previously selected S&P 500 options model. It fixes the configuration using validation results, refits that configuration on pre-holdout data, and registers predictions for the holdout…
This utility describes a method for explaining strategy returns with Fama–French three-factor or five-factor models, optionally including momentum. It aligns daily factor data with strategy returns, detects the return frequency, and compounds factor returns…
This analysis compares registered model families on a cross-asset ETF panel using walk-forward validation results. Models predict 21-trading-day returns and are assessed by cross-sectional information coefficients, which measure how well forecasts rank funds…
This notebook tests a two-model exit design on hourly BTC, ETH, and SOL perpetual data. An entry classifier identifies unusually strong forward returns; its predicted probability then joins technical features in a separate model that estimates whether the…
This notebook analyzes NASDAQ TotalView-ITCH messages to describe market-wide activity and create reusable trade data. It counts messages by type, then enriches order-execution messages by mapping stock-location identifiers to tickers and order references to…
This document describes dataset utilities for preparing time-series panels for model training and rolling inference. The training dataset returns sliding sequences of features, forward returns, volatility scales, and masks, with configurable sequence length,…
This notebook builds price-derived features for ranking a broad US stock universe. It describes momentum, volatility, moving-average, and technical-indicator families, then evaluates them against a one-session forward-return label. Its central design rule is…