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 exploratory analysis examines the legacy Quandl WIKI US equities panel, focusing on price conventions, data coverage, and what its history can support in a backtest. It distinguishes raw prices, which reflect traded price levels, from adjusted prices…
This notebook assesses how transaction costs affect a fixed CME futures configuration selected elsewhere in the research process. It applies an all-in cost grid, splitting each level evenly between commission and slippage, and carries the selected risk…
This document describes a CME futures dataset with hourly and daily bars, continuous front-month contracts, and two deferred tenors across several product groups. It explains the dataset’s coverage, fields, loading options, and related weekly CFTC…
This notebook treats a Sharpe ratio as an estimate with sampling uncertainty. It develops confidence intervals and probabilistic Sharpe calculations that account for sample length, skewness, and kurtosis, then uses minimum track record and power planning to…
This notebook compares PyPortfolioOpt, Riskfolio-Lib, and skfolio by fitting portfolio allocators on a shared ETF return panel and evaluating their frozen weights on later observations. It covers mean-risk, tail-risk, hierarchical risk parity, and penalized…
This notebook compares three ways to classify financial news sentences as positive, neutral, or negative: TF-IDF word and word-pair features with logistic regression, averaged pretrained GloVe vectors with logistic regression, and a pretrained FinBERT…
This shared allocation module turns cross-sectional predictions into portfolio weights. It ranks assets by score to select long positions or top and bottom baskets for long-short portfolios. Position weights can reflect conformal prediction widths, where…
This notebook constructs features from minute-level NASDAQ-100 data using three procedures: a rolling heterogeneous autoregressive regression for near-term variance forecasts, a Fourier transform to describe periodic structure in recent activity, and…
This analysis uses NASDAQ TotalView-ITCH messages to describe venue activity and build a trade table linked to ticker, side, and order attributes. It counts message types, compares trading with the much more numerous quoting and removal events, and ranks…
This dataset guide describes a workflow for obtaining FRED series, aligning observations to a daily calendar, and loading selected indicators for analysis. The examples include Treasury yields, the 10-year minus 2-year spread, VIX, employment measures,…
This document models broker and exchange order handling as a finite state machine. It defines explicit states for submission, acknowledgment, acceptance, partial fills, cancellation, rejection, expiry, and suspension, then maps events to valid transitions. A…
This notebook assesses whether a monthly long–short strategy based on firm characteristics can be studied with a released US firm panel. It checks the data encoding, how the available universe changes over time, whether each rebalance has enough firms to…
This notebook develops the Almgren–Chriss solution for liquidating a position while balancing market impact against the risk of remaining exposed to price moves. It uses implementation shortfall relative to the arrival price, models permanent and temporary…
This notebook shows how to analyze a financial event graph without confusing when an event happened, when it became public, and when the graph pipeline extracted it. It loads timestamped 8-K relationships, measures disclosure and extraction delays, and…
The document explains how to construct trade-based microstructure features from NASDAQ trade data aggregated into intraday bars. It covers Kyle lambda, Amihud illiquidity, the Roll spread estimator, trade intensity, and order flow imbalance (OFI). It…
The document introduces latent factors as shared return drivers inferred from co-movement across futures rather than supplied as named predictors. It compares two approaches fitted within each training fold. Principal component analysis (PCA) finds linear…
The document describes how to compare validation predictions from linear, gradient-boosting, tabular deep-learning, and sequence models for S&P 500 options. Before reporting diagnostics, it checks that each registered prediction population is complete…
The document explains how double machine learning (DML) estimates whether buyer-initiated volume share affects future returns after accounting for spread, short-term volatility, and trailing returns. It residualizes both treatment and outcome against those…
This notebook turns registered NASDAQ-100 microstructure backtests into a strategy assessment without training models or rerunning backtests. It reads metrics and lineage from the registry, builds derived cohort and paired-comparison tables when needed, and…
This notebook applies a previously selected CME futures configuration to holdout predictions, using the established allocator, rebalance schedule, concentration rules, and transaction cost assumptions. Its central methodological point is to freeze those…
This notebook teaches how to decode NASDAQ TotalView-ITCH message-by-order data from its binary format into structured records. It explains the message framing and type-specific layouts, demonstrates unpacking fields, and converts timestamps expressed as…
This notebook explains how feature stores keep training data and live model inputs aligned. It describes feature views through their entity key, event timestamp, time to live, and feature columns, then contrasts point-in-time joins for historical training…
This notebook measures how a validation-selected FX strategy responds to changes in proportional transaction costs. For each prediction label, it selects a parent strategy from the signal, allocation, and risk-overlay results, then reruns that strategy…
This notebook describes how to select a CME futures case-study configuration from registered validation backtests. It pools candidates across signal, allocation, and risk-management stages, then chooses the configuration with the strongest validation Sharpe.…