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 presentation overview describes a pipeline for converting news text into numerical signals that an automated strategy can use. It identifies sentiment, relevance, novelty, event type and potential market impact as core features, with news volume, search…
This beginner guide defines day trading as opening and closing positions within the same session, partly to avoid overnight price gaps. It surveys momentum trading, scalping, and tick-based spread strategies, then outlines markets available to day traders,…
The article explains how the Average Directional Index (ADX) measures trend strength without indicating trend direction. Direction is assessed with the positive and negative directional indicators (+DI and -DI), while ADX is derived from the separation…
The article introduces ordinary least squares regression and explains why correlated predictors can make coefficient estimates unstable and hurt predictions on new data. Using the diabetes dataset from scikit-learn, it outlines a comparison between a…
This article explains the stochastic oscillator as a momentum measure comparing the latest close with a recent high-low range. It describes %K and its moving-average signal line %D, along with fast, slow, and full variants that differ in smoothing or…
This guide presents Fibonacci retracement as a charting method for estimating possible support or resistance during a pullback. A trader identifies a swing high and low, measures the size of the move, and marks commonly used retracement ratios, including…
This introduction explains deep learning as a form of machine learning built from neural networks with multiple layers. It describes the roles of input, hidden, and output layers, and how connection weights, biases, and activation functions transform inputs…
This compiled overview summarizes webinars on machine learning, factor investing, algorithmic day trading, language models, options, volatility, medium-frequency trading, and alternative data. It outlines topics rather than teaching one complete strategy, so…
This introduction explains XGBoost as a gradient boosting method that combines sequential models, typically decision trees, with later learners aimed at correcting earlier errors. It outlines classification and regression, describes model components such as…
The article introduces random walks as stochastic paths and explains how the idea relates to the claim that future stock prices cannot be reliably inferred from current prices. Simple up or down steps illustrate a random walk, while drift allows unequal…
This project describes a dispersion strategy on Bank Nifty index options and constituent bank stock options. It takes relative volatility positions using combinations of straddles or strangles: when implied correlation is high, the example suggests selling…
The tutorial describes IBridgePy as a Python wrapper that calls Interactive Brokers’ C++ API, and outlines how to connect it to Trader Workstation or IB Gateway. It explains a basic program structure in which initialization sets persistent variables and a…
This interview follows Mark Rendle’s path from engineering and a long career in the energy industry to personal algorithmic trading. After entering markets during the late-1990s bull run and suffering a sharp reversal in 2000, he concluded that enthusiasm…
The article surveys how traders identify and control exposure to market and operational shocks. It discusses diversification, portfolio optimization, position sizing, hedging, stop-loss orders, and take-profit rules, with an opening recommendation for…
This tutorial introduces pandas as a toolkit for working with labeled one-dimensional Series and two-dimensional DataFrames. It shows how indexes can be implicit or specified, how dictionary keys can become Series labels, and how operations between Series…
This guide outlines portfolio analysis as a way to assess absolute and benchmark-relative performance alongside risk. It introduces holding-period return, arithmetic mean, Sharpe ratio, alpha, tracking error, information ratio, and Sortino ratio, then…
The article introduces the Gaussian, or normal, distribution through its mean, variance, symmetry, and probability density function. It connects the distribution to financial modeling, describing Bachelier’s random-walk view of price changes and the use of…
The document explains the Ichimoku Cloud as a charting system built from five lines calculated from price highs, lows and closes over different lookback periods. Two leading spans form the cloud, while the other lines provide conversion, base and lagging…
The document introduces Backtrader, an event-driven Python framework for strategy backtesting, visualization and connections to selected live brokers. It explains the role of the Cerebro engine, data feeds and the strategy class, including how initialization…
The document teaches how heatmaps can display financial data as colored cells, focusing on two uses: comparing single-day percentage price changes across stocks and viewing correlations among stock price changes. Its Seaborn workflow organizes stock symbols…
The document presents the Sharpe ratio as excess investment return divided by return volatility, and explains how the measure supports comparisons of strategies and portfolios. It describes annualizing a ratio from periodic returns and gives a worked…
The document explains how the Augmented Dickey-Fuller test can help assess whether the residuals between two securities are stationary, a condition used in pairs trading. It introduces stationarity, non-stationarity, unit roots, and the test’s null and…
This article compiles research papers, books, and other learning resources on reinforcement learning in finance, with expert recommendations attributed to Paul Bilokon. The cited applications include option hedging and dynamic replication, wealth management,…
The guide explains hierarchical clustering as an unsupervised method that builds nested groups and displays their relationships in a dendrogram. It contrasts clustering with supervised classification and compares hierarchical clustering with K-means: K-means…