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 explains how to inspect a shipped panel of economic series from FRED and interpret its calendar-day grid, metadata, and derived columns. Because the panel has been flattened onto a daily calendar, row counts conceal the source release…
This notebook treats ARIMA forecasts as input columns for later models rather than as standalone predictions. It fits models to ETF returns, uses stationarity checks and autocorrelation diagnostics to propose orders, and compares candidate orders with an…
This notebook describes how to prepare and register NLinear forecasts for FX labels. NLinear subtracts the last observed level from each fixed-length input history, focusing the model on changes within the lookback. A shared sequence eligibility process…
This shared analysis utility supports comparing trading-model predictions through registry metrics and prediction-level diagnostics. It loads precomputed information-coefficient results, optionally filters by label or model family, and by default excludes…
The document sets out how to construct forward-return labels for a cross-sectional futures strategy that ranks products by term structure. It distinguishes roll-adjusted prices, which are appropriate for returns across contract rolls, from raw settlement…
The document describes three model-based features built from futures carry: an ARIMA forecast of next-session carry, rolling Fourier measures of selected cycle lengths, and a two-state hidden Markov model that infers the market regime from average carry. Its…
The document explains two ways to estimate bid-ask spreads when only daily OHLCV data is available. Corwin-Schultz compares high-low ranges over adjacent one-day and two-day intervals, using the different behavior of volatility and spread to separate them;…
This document explains a validation baseline for model predictions on CME futures. At each weekly decision, products are ranked by predicted return; the top group is held long and the bottom group short, with equal weight within each leg. The number of…
The document describes converting rolling ETF return windows into two-channel images for a conventional convolutional neural network. A Gramian angular field maps normalized observations to angles and records pairwise angular relationships; a Markov…
This document introduces the Chen, Pelger, and Zhu monthly US equity panel used to benchmark asset-pricing models. It describes 46 firm characteristics grouped by economic theme, next-month excess returns, and the panel’s time-ordered train, validation, and…
The document explains a temporal convolutional network for predicting crypto perpetual funding premiums from a 60-settlement window. Four causal convolution blocks use a kernel of three and dilations of 1, 2, 4, and 8. Their receptive field spans 61…
This notebook describes a GT-GAN-inspired architecture for synthesizing time series with genuinely irregular timestamps, such as tick, volume, or dollar bars. A GRU-ODE encoder maps observations into latent states, while ODE-based generator and discriminator…
This notebook presents a workflow for characterizing market series before modeling. It begins with plots of SPY prices and returns, VIX levels, and the return distribution to identify trends, volatility clustering, and heavy tails. It then explains how to…
This notebook uses SPY daily returns to explain frequency-domain analysis and its limits as a source of trading features. A wavelet decomposition separates variation into bands at successively slower time scales, while spectral estimates describe how return…
This notebook outlines an operational workflow for connecting a strategy to Interactive Brokers through TWS or Gateway. It checks that the session is a paper account, reads account values and positions, and requests historical bars to initialize strategy…
This notebook compares three ways to use market regimes in a forecasting model: omit regime information, add the filtered probability of a volatile state as a feature, or fit separate experts for hard-assigned regimes. It builds regime probabilities from a…
This notebook sets out a process for evaluating a challenger model in shadow mode before it receives capital. It compares stored predictions from a fixed incumbent and candidate, constructs equal-weight ranked long-short books, applies the same…
This notebook surveys EdgarTools for exploring SEC filings and extracting structured company data. It explains how to identify filers by stable CIK, retrieve filings by form, and turn XBRL-tagged annual reports into financial statement tables. It also covers…
This case study uses linear models as a baseline for predicting forward returns across a broad US equity panel. It explains why overlapping price and volume features create collinearity, making ordinary least squares coefficients unstable, and compares Ridge…
This analysis compares registered double machine learning treatment effects from nine trading case studies. It loads current results from each study’s registry, checks registry integrity and duplicate labels, and makes coverage explicit. Effects and…
This notebook presents a framework for assessing an ETF allocation backtest using daily portfolio returns and a matched SPY benchmark. It covers risk and return measures such as Sharpe, Sortino, Calmar, and maximum drawdown; rolling metrics; drawdown…
This notebook explains how model uncertainty can add information beyond a point estimate. It fits a stochastic volatility model in which latent log volatility evolves over time and returns follow a Student-t distribution. Posterior spread, interval width,…
This notebook introduces futures backtesting mechanics through a long-short momentum example across several asset classes. It explains how contract specifications convert price movements into dollar profit and loss through multipliers, and how notional…
This evaluation harness separates four kinds of failure in a financial retrieval-augmented generation pipeline: retrieving relevant evidence, grounding answers in that evidence, refusing unanswerable questions, and resisting unsafe instructions in retrieved…