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.
243 documents
This notebook reports parity comparisons between Backtrader, Zipline Reloaded, and an internal trading framework on selected real case-study strategies. It includes ETF and US equity-panel comparisons for both external engines, plus CME futures and…
This module defines a monthly ETF allocation baseline using a risk-adjusted momentum score: trailing cumulative return divided by annualized realized volatility. It selects the highest-ranked assets when the 10-year minus 2-year yield-curve slope exceeds a…
This demonstration describes the operational shape of a continuously running crypto strategy connected to a USD spot broker. It maps a larger perpetual-futures case-study universe to the smaller set of available spot pairs, then routes a momentum z-score…
This overview consolidates configuration data from nine trading case studies spanning equities, crypto, foreign exchange, futures, options, and multi-asset portfolios. It compares each study’s universe, data frequency, decision cadence, cost model, and…
This notebook presents a deterministic framework for checking whether backtest and live trading pipelines behave consistently. It compares the stages that turn price bars into decisions: feature calculations, predictions, signals, and order sizes. A fixed…
This notebook trains a reinforcement learning agent to schedule a fixed sell order across hourly bars from a crypto perpetual futures market. Its state includes lagged returns, volatility, prior-hour volume, the perpetual premium to spot, and time until…
This notebook uses NASDAQ ITCH-derived trade and order data to illustrate microstructure patterns. It examines negative first-order autocorrelation in tick-level trade returns, comparing the effect with mid-price returns, and contrasts trading activity and…
This demonstration extends a single-order workflow into a daily rebalance for a fixed universe of large-cap US stocks. It explains how to compare current broker positions with model targets, construct orders for the differences, and optionally submit the…
This case study evaluates short at-the-money straddles on S&P 500 constituents, entered weekly and held until expiry with a daily delta hedge. Its main methodological choice is to model hold-to-maturity returns: the option position incurs an entry spread but…
This notebook evaluates how transaction-cost assumptions affect the validation Sharpe of one selected S&P 500 equity and options allocation. It carries forward the configuration chosen through a frozen candidate set when available, then reruns the same…
This NASDAQ-100 case study investigates whether 15-minute microstructure signals can survive trading costs. The workflow evaluates order flow, quote staleness, and relative spreads, then compares a full-universe strategy with one restricted to…
This notebook checks whether a daily US equity ranking strategy has enough usable data for a fair evaluation before fitting any model. It explains how to form a point-in-time universe with historical constituents, using printed prices and prior-session…
This document presents a cost sensitivity analysis for a fixed ETF momentum strategy. It holds the universe, weights, schedule, and simulator constant while rerunning the backtest over a range of per-leg fees. The resulting curve shows how Sharpe ratio and…
This notebook demonstrates how a broker wrapper can reject unsafe orders using order-size and position limits, order-rate caps, asset restrictions, and a persistent kill switch. A synthetic broker makes the decisions observable: attempted orders are either…
This analysis profiles a fixed universe of 100 ETFs across nine asset groups. It checks coverage by fund and year, confirms that the price panel matches the group configuration, reviews nulls and OHLC ordering, and compares trading volume across groups. It…
This notebook explains how to rebuild a single-symbol NASDAQ limit order book from message-by-order data. It processes adds, executions, cancellations, deletes, and replacements while maintaining the remaining size of each live order. Replacements require…
This source module provides loaders for U.S. equity prices, index data, options, market microstructure, fundamentals, and institutional holdings. Its most substantive methodological detail concerns resampling intraday trade data: open, high, low, close, and…
This notebook demonstrates a shared OHLCV interface across Yahoo Finance, a long-history U.S. equity archive, and FRED macroeconomic series. It builds an ETF universe for a later rotation case study, shows how to combine historical and current sources, and…
This notebook develops a unit-aware framework for estimating trading costs across equities, ETFs, futures, foreign exchange, and crypto perpetuals. It first distinguishes traded volume from activity measures that cannot be converted into dollar turnover,…
This notebook reprices leading ETF allocation configurations across two cost grids while holding predictions, concentration, and allocation rules fixed. It compares the case study's per-share commission and half-spread model, which reflects how ETF trading…
This notebook measures how execution costs affect the already selected crypto perpetual futures configuration. It holds the model, checkpoint, entry rule, allocation, and risk control fixed, then reruns backtests across a grid of round-trip charges on traded…
This notebook builds a monthly ETF rotation backtest from portfolio returns through to simulated trades. It ranks ten funds using trailing risk-adjusted returns, applies a Treasury yield-curve regime to choose between the leaders and a defensive bond…
This notebook reconstructs the prevailing best bid and offer for each AAPL trade during a single March 2020 session, then applies the Lee–Ready method to infer whether buyers or sellers initiated trades. It interleaves quote and trade events in timestamp…
This notebook builds an auditable report for a long-only Bitcoin strategy that enters and exits using RSI thresholds. It compares gross and net results, then measures performance against a buy-and-hold benchmark run with the same data, warmup, exposure,…