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 guide describes a walk-forward workflow for forecasting stock prices with XGBoost. It motivates repeated model updates as a response to concept drift and changing data distributions. Historical price data are cleaned, adjusted prices are used, and…
The article explains the conditions commonly used to justify ordinary least squares regression and why they matter for estimation and inference. It covers linearity in the model parameters, lack of perfect multicollinearity, independent errors, constant…
This project describes a framework for classifying market conditions with a Random Forest and adapting capital allocation to the detected regime. It uses historical Nifty 500 data and market breadth features intended to capture cross-stock momentum, trend…
This tutorial outlines a TensorFlow multilayer perceptron that predicts whether Tata Motors’ next daily close will rise. It derives eight inputs from daily OHLC data: price spreads, moving averages, short-period volatility, RSI, and Williams %R. The target…
The document presents an adaptive Bitcoin strategy that first infers market regimes from daily returns with a Hidden Markov Model, then uses a regime-specific Random Forest classifier to predict the next day’s direction. Within a rolling historical window,…
The article explains algorithmic trading as using defined instructions to generate signals and place or manage orders, then argues that learning it requires programming, market knowledge, analysis and backtesting. Its practical example describes reading…
This overview introduces several methods for modeling financial data when a straight-line relationship is inadequate or the target is not a continuous average. It describes logistic regression for binary outcomes, including interpreting its output as a…
The document introduces decision trees as supervised models for classifying a stock’s next daily move as up or down. It outlines a workflow using historical OHLCV data, technical indicators such as RSI, moving averages and ADX, and a target class derived…
The article describes how MBA graduates might move into algorithmic trading and identifies skills that can transfer, including business judgment and awareness of ethics and compliance. It recommends building stronger knowledge of markets and trading…
This project tests active management of a Big Tech stock portfolio against equal-weight buy-and-hold and monthly rebalancing baselines. It uses online linear regression, principal component features, and a Kalman filter to estimate each stock’s value…
This project describes a machine-learning system that uses a decision tree to generate binary signals for trading individual stocks. Indicator buy triggers are used as inputs, while indicator sell rules are omitted to keep the model focused; a zero signal…
This article surveys an end-to-end approach to applying machine learning and artificial intelligence to trading. It advocates starting with a trading objective, selecting a model only when it adds value, and interpreting model outputs in the context of…
This interview profile describes a trader and strategy researcher’s plan to help establish a high-frequency trading desk within a broader systematic trading fund. The intended focus is short holding periods in Asian and European markets, drawing on machine…
This interview presents a quantitative analyst’s path from engineering and statistics studies into quantitative finance, including work in high-frequency trading, banking, and strategy research. Its central lesson is to research markets carefully before…
The document introduces Bayesian classification and applies a Bernoulli Naive Bayes model to a long-only stock trading example. The features are binary signals derived from RSI and the stochastic oscillator; the target labels whether the following day's…
This project describes a cloud based automated system for WTI futures that uses machine learning to classify market conditions as trending or ranging. Several models vote within separate trend and range groups; when the groups disagree, their confidence…
The article describes a shift in Indian financial engineering education from broad, long-duration programs toward focused training in areas such as quantitative and algorithmic trading. It outlines traditional subjects including quantitative methods, equity…
This article is a curated overview of resources on sentiment analysis for trading rather than a single strategy or empirical study. It points readers to approaches that use news, social media, earnings information, macroeconomic data, and other sources to…
This project applies a Random Forest classifier to intraday BTC/USD data to produce directional signals from technical features. It uses two years of one-minute OHLC observations and inputs including returns, percentage changes, RSI, ADX, moving-average…
This article turns machine-learning predictions into a rule-based EUR/USD strategy and compares its historical performance with buy and hold. Its indicators are Parabolic SAR, which trails price and reverses after a price break, and the MACD histogram,…
The document introduces convolutional neural networks (CNNs), explaining how convolutional filters create feature maps, pooling reduces dimensionality, and fully connected layers support classification or regression. It surveys several well-known CNN…
The article compares two unsupervised clustering methods using daily RSI and ADX observations as an example for grouping stock behavior into possible bullish, bearish, and sideways regimes. K-means assigns observations to the nearest of a chosen number of…
The article presents data cleaning as a necessary stage between acquiring raw data and analyzing it or training machine learning models. It explains tidy data structure, variable types, and the importance of preserving the original source data alongside a…
The article introduces supervised and unsupervised learning, then focuses on supervised classification, where models learn from labeled examples to assign observations to categories. It distinguishes binary, multiclass, and imbalanced classification and…