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.
511 documents
This introduction explains why financial prices are modeled as stochastic processes rather than deterministic functions. It reviews the calculus chain rule, distinguishes deterministic and random processes, and introduces Brownian motion through the analogy…
The article surveys ways to choose trade size, beginning with account risk, the amount of capital exposed to loss, and trade risk, the distance between entry and a stop. It contrasts fixed units, fixed dollar amounts, fixed percentages of account value, and…
The article explains why raw datasets need cleaning and transformation before machine learning, with examples framed around trading data. It discusses missing values, outliers, categorical features, inconsistent date formats, and overfitting. Suggested…
A fill-or-kill order is described as a limit order that must be executed immediately for the full requested quantity or cancelled entirely. It does not permit a partial execution. The document contrasts this behavior with immediate-or-cancel and all-or-none…
The document introduces live trading as placing real orders in current markets, and distinguishes it from simulated practice. It surveys day trading, swing trading, momentum, breakout trading, and scalping, describing their typical holding periods or entry…
The document argues that strategies should be evaluated as components of an investment portfolio, rather than judged only as standalone systems. Standard measures such as CAGR, Sharpe ratio, and maximum drawdown summarize performance but do not show the…
The article explains why implied volatility can vary across option strike prices instead of remaining flat as in the Black-Scholes-Merton model. It attributes the smile partly to real asset returns having more extreme moves than a lognormal model predicts,…
This project describes a stock pairs strategy that periodically selects candidate pairs based on whether their price spread appears stationary. It estimates a hedge ratio with linear regression, forms a spread, and applies an Augmented Dickey-Fuller test to…
The document introduces the Johansen cointegration test as a way to assess long-run relationships among several time series. It explains that the trace and maximum eigenvalue tests use eigenvalues to estimate the number of cointegrating relationships, and…
The document is an outline for a webinar introducing machine learning in quantitative finance. It lists an overview of machine learning and its workflow, features of the Quantiacs toolkit, and a demonstration applying machine learning to futures data. The…
The document describes a simple trend-following system built with linear regression. It introduces ordinary least squares and explains rolling regression as fitting a model repeatedly using a recent window of candles. In the example, the model relates each…
The document outlines how to build and tune an indicator-based trading strategy. It explains selecting indicators that fit a trading approach, learning their signals and limits, defining rules, testing parameters on historical data, and monitoring the…
This guide compares free and paid sources of financial data by access method, asset coverage, and availability of intraday, daily, fundamental, and news information. It recommends choosing a provider according to data accuracy, latency, historical depth,…
This event overview outlines advanced algorithmic trading topics covered in a two-day NSE management program for financial institution leaders and experienced practitioners. Its strategy survey includes high-frequency trading, market making, structural and…
Time-weighted average price (TWAP) is presented as an execution approach for dividing a large order into smaller trades scheduled across a chosen period. The article illustrates this with alternative schedules for buying 10,000 shares and notes that varying…
The article outlines the development of the Fama-French five-factor asset-pricing model from CAPM and the three-factor model. Alongside market, size, and value effects, the five-factor version adds profitability and investment. The article frames these…
This beginner guide explains how to install the TA-Lib Python library across Windows, macOS, and Linux. It recommends using a Conda environment where possible and outlines platform-specific steps, including checking the Python version and system architecture…
This project describes a long-only strategy that seeks to capture overnight price gaps in Indian equities. It enters at the close after a session with a larger true range than the previous session, a positive close-to-open move, and a daily change within a…
The article defines market inefficiency as a divergence between an asset’s traded price and its fair value, and links such gaps to crises, earnings information, speculation, and delayed investor reactions. It uses the dotcom boom and the U.S. housing and…
Expected Shortfall (ES), also called Conditional Value at Risk, measures the average loss in the tail beyond a chosen Value at Risk (VaR) threshold. The article explains the distinction: VaR identifies a loss cutoff at a confidence level, while ES estimates…
The document outlines a daily sentiment-based strategy for China A-share stocks using posts from recognized financial accounts on Weibo. It proposes collecting posts during the pre-market period, considering four actively discussed sectors, and identifying a…
The article presents a simplified Turtle-style strategy coded for equities. It enters long when the close exceeds a recent rolling high and short when it falls below a rolling low, then exits when price crosses a rolling mean. Signals are carried forward to…
The article explains Gini impurity as a measure of class mixing in a decision tree node. It gives the formula one minus the sum of squared class probabilities, then describes evaluating a candidate feature by calculating each resulting branch’s impurity and…
The article introduces Bitcoin’s public blockchain, mining, capped issuance, and wallet transactions, then connects these features to ransomware payments and Bitcoin’s appeal as a tradable asset. It frames price as primarily demand-driven and names…