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.
742 documents
This notebook tests how a selected US firm characteristics strategy responds when its transaction cost assumption changes. It holds the strategy configuration fixed and reruns validation backtests across a declared grid of commission and slippage levels,…
This document describes a reader-facing interface for examining backtest results stored in a registry. It supports summaries of run counts, inspection of specifications and individual runs, ranking results, comparing allocation methods, viewing concentration…
This notebook runs a fixed equity-characteristics strategy on a reserved holdout period using predictions and a portfolio allocator selected earlier. It keeps the configuration, position sizing, concentration, rebalance cadence, and cost assumption…
This notebook analyzes timestamped financial event edges from a knowledge graph, distinguishing when an event happened, when it became public, and when the extraction pipeline created the edge. It calculates disclosure and extraction lags, builds snapshots…
This notebook develops a unit-aware framework for estimating trading costs across equities, crypto perpetuals, futures, ETFs, and foreign exchange. It distinguishes share volume, contract volume, base-asset volume, and price-update counts, converting…
This chapter review describes a hypothesis-driven process for defining trading strategies before backtesting. It connects documented data assumptions and immutable configuration to exploratory analysis, event studies, and a structured strategy term sheet.…
This notebook explains how futures contract specifications affect backtest accounting. It shows how the contract multiplier converts price moves into dollar P&L, how price times multiplier determines notional value for sizing, and why per-contract…
This notebook compares reference ETF portfolios under historical crises, hand-defined simultaneous asset shocks, and Monte Carlo loss scenarios. Historical windows include major equity and rate-driven selloffs, with portfolio returns compounded over explicit…
This case study assesses a weekly S&P 500 options short straddle using registered backtests. It selects a configuration from a nominated liquid universe, ranks candidates on validation, and evaluates the chosen configuration on holdout data without using…
The document describes a shared analysis workflow for comparing model configurations across case studies. It first selects one configuration per case study, then derives fold-level and cross-study summaries from that selection so later analyses use a…
This audit record defines how several backtesting frameworks are compared with ML4T across real strategy case studies and a synthetic stress workload. It specifies the comparison rules for ordered fills, timestamps, account-money values, quantities, and…
This notebook presents correctness and runtime comparisons for VectorBT Pro and VectorBT OSS against ML4T on supported case-study strategies. It covers ETF allocation, USD-quoted foreign exchange, and a US equity panel for both editions; VectorBT Pro also…
This notebook turns stock-level predictions into validation portfolios. On each rebalance date, it sorts stocks by predicted return, buys the top group and shorts the bottom group, and assigns equal capital to every position. It applies this baseline across…
This notebook defines forward price-return labels for a fixed panel of crypto perpetual contracts and explains how label construction affects every later model and backtest. It shifts bar-open timestamps to the time completed data becomes available,…
This source module builds catalog tables from experiment registries for model predictions and backtests. It defines reserved fields for provenance, identity, completion status, artifact availability, and metrics. The catalog carries multiple measures that…
This notebook demonstrates how a fixed dollar order can impose very different costs across stocks because its size relative to available trading volume matters. It applies a square-root market-impact model to a long-when-positive momentum strategy using…
This notebook evaluates LSTM and NLinear sequence configurations on CME futures products. Sequence models consume ordered windows of observations, testing whether the recent path contains information beyond engineered summary features. The LSTM learns a…
This notebook describes a shared workflow for fitting temporal convolutional networks to daily FX pair data. Instead of treating each date as an isolated feature row, the model uses a fixed lookback of consecutive observations. The runner determines eligible…
This case study evaluates daily momentum and carry signals across a small, correlated universe of G10 spot currency pairs. Its workflow moves from feasibility checks and forward-return labels through engineered and model-based features, cross-validation,…
This notebook adapts TSMixer to predict forward ETF returns from historical momentum features. Its architecture alternates a shared linear transformation across the time axis with a feature MLP applied separately at each date. Pre-normalization and residual…
This notebook explains why a strategy’s observed Sharpe ratio needs adjustment when it was selected from many trials. It presents the Deflated Sharpe Ratio (DSR), which compares the selected result with a benchmark that rises with the number and dispersion…
This notebook adapts a supervised autoencoder to daily US equities. The model reconstructs ranked price and volume characteristics while auxiliary and main classification heads train a shared latent representation to predict whether returns are positive…
This notebook presents a workflow for reducing a large set of ETF features to candidates for later modeling. It ranks features using cross-sectional Spearman information coefficients against forward returns, computed by date and then averaged. Newey–West…
This notebook studies TabM, a neural network design for tabular data, on monthly firm characteristics. It compares three presets that increase hidden width and ensemble membership while keeping other training settings fixed. The shared runner fixes the…