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.
122 documents
The document examines Bitcoin return distributions and volatility, then outlines a modeling workflow using ARMA for returns and EGARCH for conditional volatility. It calculates log returns from closing prices and discusses descriptive statistics, quantile…
This tutorial develops a pairs trading approach around the idea that two related assets may have a stable long-run relationship even as their prices temporarily diverge. It distinguishes cointegration from correlation, uses a cointegration test to screen…
This tutorial outlines a data-mining approach to machine-learning signals, contrasting it with strategies that begin from an explicit market inefficiency such as trend following or mean reversion. It recommends defining the prediction target and evaluation…
The article describes a workflow for finding tokens held across wallets associated with holders of a successful project. It automates collection of leading BSC token holders, filters out likely institutions and large project wallets, queries remaining…
This tutorial develops an intraday pairs-trading example using SPY and IWM minute bars. It aligns the two price series, estimates a rolling linear-regression hedge ratio, forms a spread, and standardizes that spread as a z-score. The example opens a long…
The article introduces Markowitz modern portfolio theory as a framework for choosing asset weights by balancing expected return and risk. It explains that portfolio risk depends not only on each asset’s volatility but also on covariance between assets, so…
This tutorial explains how to retrieve a specified number of historical bars when an exchange API limits the amount returned by a single request. Its example targets Binance futures: map supported bar durations to exchange intervals, request successive time…
This article explains two signals derived from limit order books: volume imbalance at the best bid and ask, and order flow imbalance based on changes in displayed size and quote prices. The first compares the quantities resting at the best buy and sell…
This article studies whether crypto assets that move more closely with Bitcoin perform differently from less correlated coins. It explains Pearson correlation as a measure of linear co-movement, then describes collecting four-hour Binance futures prices for…
This article outlines a way to screen cryptocurrencies for grid trading, which seeks to trade repeated price swings rather than rely on a sustained directional move. It proposes looking for assets with substantial price ranges and restrained cumulative…
This guide extends a market data collector so FMZ’s backtest system can request historical bars from a custom source. The collector stores exchange K-line data in MongoDB while a small HTTP service runs alongside it. When the backtester requests data for a…
This article describes a workflow for finding tokens held across wallets associated with early holders of a successful BSC project. It automates the manual process of collecting top holders, excluding labeled institutions and large project wallets, querying…
This introduction contrasts subjective trading, where a trader interprets signals and may change methods after losses, with quantitative trading, where rules are applied consistently and strategies are evaluated with historical data. It presents…
The document explains how to combine existing candles into a larger target interval when an exchange or data source does not provide that interval. Its example infers the source interval from the final two records, checks that the requested interval is an…
This introductory course explains quantitative trading as the use of rules, data, and computation to research and execute investment decisions. It contrasts systematic execution with discretionary judgment, while emphasizing that automation is a tool and…
This article describes a quantitative prediction workflow that turns each recent candlestick window into a tabular sample for TabFM, a foundation model for tabular data. Each row contains OHLCV values from completed bars, arranged as lagged fields, and the…
The document compares China’s commodity futures CTP interface with cryptocurrency exchange APIs. It covers historical data availability, communication patterns, market depth and trade reporting, request limits, and operational reliability. CTP generally…
The paper develops a framework for assessing high-frequency trading returns by separating four contributors: available price opportunity, the fraction captured by a strategy, effective spread paid or earned, and liquidity-provider rebates. It compares three…
This document explains a statistical arbitrage approach that trades two correlated cryptocurrencies when their price ratio moves away from a reference level. It describes taking opposite positions in the two assets and closing or adjusting them as the ratio…
The document explains why a profitable historical backtest may fail in live markets, especially when a strategy is tuned and judged on the same limited sample. It recommends splitting chronological price history into an earlier training segment for parameter…
The article explains a backtest performance function that turns starting capital, cumulative profit observations, timestamps, and annual trading days into total and annualized returns, Sharpe ratio, volatility, maximum drawdown, and win rate. It walks…
This article outlines a Fisher Transform indicator computed from bar highs and lows. It normalizes the midpoint against the highest high and lowest low over a lookback period, blends that value with the prior normalized value, clamps extreme inputs, and…
This article develops adjusted mid-price estimates from high-frequency order book and transaction data. Using top-of-book bid and ask quantities, it starts with the standard midpoint and tests volume-weighted and nonlinear imbalance adjustments. It then…
The article introduces Bayesian statistics through its historical development, from De Moivre’s forward probability questions to Thomas Bayes, Richard Price, and Laplace’s work on inverse probability. The central idea is to infer an unknown parameter from…