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.
566 documents
This notebook demonstrates feature-drift checks on ETF momentum and technical features across calm and stressed windows, and on crypto perpetuals with premium-index data across market regimes. It compares Population Stability Index (PSI), including its…
This notebook evaluates TSMixer as a global sequence model for an ETF panel. The model shares parameters across funds while using each fund’s own history and covariates; its mixing layers learn temporal and within-series relationships without combining one…
This notebook describes using TSMixer to predict stock returns from ordered windows of each stock’s features. Each example contains 60 consecutive sessions; windows that cross gaps in a stock’s history are excluded, so the number of usable examples varies…
This guide organizes US equity datasets into market data, company fundamentals, investor positioning, and firm characteristics. It inventories loaders for daily and intraday bars, options, and market microstructure records, as well as SEC filing text, XBRL…
This notebook turns validation predictions from multiple model families into equal-weight, long-short portfolios. It ranks stocks by predicted return, buys the top names and shorts the bottom names, and sweeps several portfolio concentrations using a shared…
This document presents a staged process for linking company names from filings, news, and alternative data to securities. It distinguishes entity identifiers such as CIK and LEI from security identifiers such as FIGI, CUSIP, and ISIN, and explains why…
This document explains a supervised autoencoder factor model for predicting stock returns in an equity option analytics research setting. Unlike PCA, IPCA, and an unsupervised conditional autoencoder, its training objective combines reconstruction of the…
This educational analysis compares four neural network designs on the same task: predicting the next daily return from a recent window of returns. A pooled set of eight exchange-traded funds provides varied market exposures. The models differ in how they…
This notebook measures how well the Lee-Ready method infers trade aggressor direction using Nasdaq order-by-order messages with venue-provided aggressor labels as ground truth. It reconstructs the limit order book from adds, modifications, cancellations,…
This notebook evaluates NLinear, a simple sequence model that subtracts the latest observed level from a lookback window and maps the resulting sequence to a forecast with a linear transformation. It fits the ETF model population on walk-forward folds and…
This notebook presents a conditional autoencoder for equity returns in which a neural network maps stock characteristics to nonlinear factor loadings, while another network extracts contemporaneous latent factors from characteristic-managed portfolio…
This notebook explains how to rebuild a limit order book from DataBento market-by-order messages for a single NASDAQ symbol and trading day. It models each order, aggregates orders into price levels, and maintains separate bid and ask sides. Correct message…
This notebook compares six long-only ETF allocation methods designed to reduce reliance on unstable estimates. It applies Ledoit-Wolf covariance shrinkage to estimators that use covariance, and contrasts mean-variance maximum Sharpe with minimum variance,…
This chapter synthesizes nine case studies that take machine-learning signals through portfolio construction, trading costs, risk overlays, and frozen holdout evaluation. It treats each case study’s progression as the unit of analysis instead of ranking…
This assessment traces a single US equities strategy from a frozen validation backtest set to its holdout evaluation. It applies a deterministic rule: choose the candidate with the highest validation Sharpe, breaking ties by backtest hash. Registry records…
This notebook runs a selected NASDAQ-100 microstructure configuration on its registered holdout predictions. The model, allocator, concentration, rebalance schedule, risk overlay, and cost assumptions are inherited from earlier work and applied unchanged;…
This notebook compares ways to size positions in a US equities panel while holding the model, checkpoint, rebalance dates, and selected stocks fixed. Prediction-based methods scale capital by forecast magnitude or interval uncertainty; inverse volatility and…
This notebook explains how to select one strategy from a fixed set of US equity backtests and assess the resulting strategy on a separate holdout period. It validates that candidates share the required data and protocol identities, then ranks them by…
This notebook demonstrates an operational workflow for connecting a shared backtest and live strategy to an Interactive Brokers paper-trading session. It checks account identity and state, requests historical bars to initialize indicators, subscribes to…
This notebook compares three linear time-series models, a Transformer encoder, and parameter-free forecasts on daily SPY returns. The linear approaches map a historical window to a multi-day forecast, with variants that separate a smooth component from its…
This notebook examines whether gradient-boosted trees can find nonlinear relationships in NASDAQ-100 microstructure features that a linear model may miss. It focuses on the possibility that order-flow imbalance predicts returns differently depending on the…
This feasibility analysis checks whether a daily long-short equity ranking strategy can be researched with the available US stock panel. It examines point-in-time universe construction using price and trailing turnover thresholds, compares proportional…
This notebook refits the configuration selected by earlier validation stages using pre-2021 history, then publishes predictions for a 2021 holdout. It retrieves the chosen configuration from a recorded candidate set or applies the same ranking rule when that…
This analysis introduces option-chain structure and examines a 2020 slice of S&P 500 options for eight underlyings. It explains moneyness, intrinsic and time value, Greeks, implied volatility, and the information represented by volatility skew and term…