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 explains how a neural network adjusts its weights after forward propagation produces an incorrect prediction. It defines a squared-error loss for predicted class probabilities, then describes gradient descent as repeated weight updates based on…
This project compares ARIMA time-series modeling with an LSTM neural network for next-day Nifty index price forecasts. The author used five years of adjusted closing-price data, selected an ARIMA specification after stationarity checks and parameter…
The article introduces machine learning as a way to learn patterns from data and use them to classify or predict outcomes. It outlines supervised learning with labeled examples, including classification and regression; unsupervised learning that groups…
This year-in-review lists educational and industry events related to quantitative trading. The most substantive strategy topics include momentum linked to autocorrelation and market inefficiencies, with sessions described as covering backtesting and…
The document explains simple and multiple linear regression as ways to estimate a target from one or more predictors. It presents Ordinary Least Squares as the method for fitting coefficients by minimizing squared residuals, with coefficients describing the…
The article explains why ordinary cross-validation can mislead when financial features and labels depend on overlapping time periods. Embargoing removes observations near a test fold when their feature lookbacks could draw on information from that fold.…
The article introduces Markov models, focusing on Markov chains and hidden Markov models (HMMs), and explains how they can represent random processes whose next state depends on the current state. A fully observable process can be modeled as a Markov chain;…
This profile outlines a trader’s progression from computer engineering and robotics into systematic trading. It describes an interest in using unsupervised learning to uncover structure in market data, then reinforcement learning to train a neural network…
This article proposes an accessible self-study path for people interested in systematic trading. It groups suggested books and learning resources around Python and Pandas, market fundamentals across asset classes, machine learning, technical and fundamental…
The document introduces RAPIDS, a set of NVIDIA GPU libraries for data science, and explains the roles of cuDF for dataframe operations, cuML for machine learning, and cuPy for numerical arrays. It outlines system and installation requirements, then…
The article contrasts technical analysis with quantitative research in algorithmic trading. It describes technical analysts as using historical market behavior and indicators to form directional signals, while quants build and assess systematic strategies…
The document introduces the Bag of Words (BoW) method for representing text as counts of vocabulary terms. It outlines basic preprocessing and explains how a document collection becomes a matrix in which rows represent documents, columns represent unique…
The article surveys ways artificial intelligence is being used in quantitative finance, including automated trading, risk analysis, portfolio management, market prediction, fraud detection, and high-frequency trading. It describes how quant work has shifted…
This overview curates Python resources for quantitative and algorithmic trading rather than developing one strategy. The listed topics include market-data retrieval and visualization, technical indicators, VaR estimation, machine-learning classification,…
The article introduces LightGBM, a tree-based gradient boosting method, and explains its leaf-wise tree growth, Gradient-based One-Side Sampling, and Exclusive Feature Bundling. It also describes histogram binning, categorical feature handling, and selected…
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…
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 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…
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…
This project describes a long-only portfolio that reallocates capital among a small basket of sector or asset ETFs and cash on a fixed weekly schedule. It compares classifier-based allocations with a rule-based momentum baseline. The baseline averages recent…
This beginner guide outlines a machine-learning workflow for classifying whether the S&P 500 will rise or fall on the next trading day. It introduces classification and distinguishes binary, multiclass, and imbalanced problems, then describes a practical…