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.
5,018 documents
This tutorial develops a simple S&P 500 trading signal using a support vector classifier. It derives two predictors from historical open, close, high, and low prices, labels the next day according to whether the index rises, and splits observations into…
This tutorial presents a basic classification workflow using scikit-learn and the Iris dataset. It explains how features and labels are represented, why data should be split into training and test sets, and how a k-nearest neighbors classifier is created,…
The article introduces ARFIMA models, which extend ARIMA by allowing the integration parameter to be fractional. This lets the model represent persistent dependence, or long memory, that may be diminished when prices are converted to returns through ordinary…
This interview follows an engineer and AI practitioner as she moves into quantitative trading and develops an algorithmic trading desk focused on crypto. Her account highlights a practical learning path: apply statistical and machine-learning methods to…
This overview answers common questions about algorithmic trading, explaining that algorithms turn inputs and explicit rules into repeatable outputs and can determine trade timing, price, or size. It distinguishes algorithmic strategy design from automated…
The document explains the difference between syntax errors, which prevent code from being parsed, and exceptions, which arise when syntactically valid code encounters a problem during execution. A division function illustrates runtime failures such as…
This profile describes Ryan Soriano’s experience learning automated trading, including a course focused on connecting Python strategies to Interactive Brokers. He highlights practical steps such as linking to the broker for paper and live trading. His stated…
The document surveys neural network concepts and architectures relevant to trading, including perceptrons, feed-forward networks, multilayer perceptrons, convolutional networks, recurrent networks, and modular networks. It explains their broad structural…
This interview presents one learner’s route from long-term investing and manual indicator-based trading into algorithmic trading education. The interviewee describes choosing a structured course to study a range of subjects, including statistics, options,…
The article introduces Bayesian statistics as a way to update beliefs about market hypotheses and model parameters when new evidence arrives. It explains priors, likelihoods, and posterior probabilities, then works through a simplified earnings scenario in…
This interview describes how Pranav Lal, who is blind, uses screen readers and programming tools to study and run algorithmic trading systems. He contrasts the effort of interpreting charts with a workflow based on accessible command-line tools, code, price…
This overview traces computing from early mechanical calculators and punched-card systems through programmable computers, telecommunications, personal computing, and machine learning. It describes milestones such as the Pascaline, Babbage’s engines,…
Boruta-Shap combines Boruta’s comparison of original features against shuffled versions with Shapley-based importance estimates. The described workflow uses a tree-based model to assess tentative features across repeated trials, counts how often features…
This interview traces Vijayakumar’s progression from early stock investments and repeated losses to options trading and work on algorithmic strategies. He describes learning through books and practice, then studying derivatives, Python, and quantitative…
The document explains Python’s lambda expressions as short, unnamed functions that evaluate one expression and return a value. It contrasts them with named functions defined in blocks, noting that lambdas suit small, single-purpose operations but cannot…
This overview groups Python libraries by common tasks in quantitative trading workflows. For data access, it discusses tools for retrieving market prices, fundamentals, and economic datasets, along with a broker interface for working with Interactive…
This tutorial describes a neural-network workflow for predicting the next stock price from daily OHLC data for an Indian listed company. It covers scaling inputs and targets, arranging observations into sequential training, validation, and test sets, and…
The document introduces sentiment analysis, also called opinion mining, as a way to classify the tone expressed in text as positive, negative, or neutral. In a trading context, this can be applied to news and other unstructured information, which automated…
The article outlines a supervised learning pipeline for forecasting the next day’s closing price of the gold ETF GLD. It uses three-day and nine-day moving averages as predictors, shifts the closing-price series to define the next-day target, and fits a…
The article explains how Quadratic Discriminant Analysis (QDA) differs from Linear Discriminant Analysis (LDA), then applies QDA to an intraday momentum strategy using three-minute e-mini S&P 500 futures data. LDA assumes classes share a covariance matrix,…
The article introduces unsupervised learning as a way to find structure in data without target labels, contrasting it with supervised prediction. Its trading example uses K-means to group stocks by return on equity and market beta. The workflow standardizes…
This project uses computer vision to classify the next trading day’s direction for selected precious and industrial metals. It turns fixed windows of daily candlesticks into 224-by-224 images and trains ResNet CNNs to predict whether the following day’s…
The article presents algorithmic trading as a way to automate responses to changing prices and reduce discretionary delays. It outlines possible uses such as entering or exiting positions under predefined conditions, using stop orders during sharp declines,…
The article introduces spaCy as a Python library for processing text, with an emphasis on its production-oriented pipelines. It contrasts spaCy with NLTK and describes a workflow using a trained language model to convert text into tokens, lemmas, sentences,…