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 tutorial uses simulated data generated from a second-order relationship with normally distributed noise to explain model underfitting, overfitting, and the bias–variance tradeoff. It divides the observations into training and test sets, fits polynomial…
This introductory guide explains how financial markets connect buyers and sellers, how participants access exchanges through brokers or direct market access, and what instruments trade there. It introduces stocks and the distinction between primary and…
This guide describes a trend-following method that calculates short- and long-window moving averages on the Nifty index, then uses their crossovers to signal long call option trades. It outlines a Python workflow: obtain index and option data, combine the…
Steven Downey describes using quantitative research to test investment beliefs rather than accepting them without evidence. His examples include examining whether gold behaves as an inflation hedge, whether oil and an energy company’s shares are related, and…
The project proposes a daily allocation strategy across stocks in India’s Nifty Bank index. It uses three dynamic linear neural network models: one estimates the probability of a positive next-day return, while two estimate return size conditional on…
Tomás García-Purriños describes a medium- to long-term approach to multi-asset investing that combines technical indicators with fundamental measures, especially macroeconomic data, and indicators of investor sentiment and market flows. He argues that no…
This tutorial introduces quantmod as an R environment for exploring market data and prototyping quantitative analyses. Using Apple stock as its example, it demonstrates fetching historical OHLCV data, viewing observations, charting prices and volume,…
The document explains the chain rule for differentiating a function built from nested functions. If one quantity depends on an intermediate quantity, which itself depends on an input, the overall rate of change is found by multiplying the relevant…
Forward propagation carries input data through a neural network to produce an output. At each layer, neurons combine inputs with weights and biases, apply an activation function, and pass the resulting values onward. The article introduces this process using…
This project outlines a statistical arbitrage approach to trading cryptocurrency perpetual contracts on Binance. It screens contract price series for stationarity and cointegration, then forms a spread between a selected pair and uses deviations from the…
The document explains how to measure realized portfolio performance and examine where returns came from. It distinguishes a single-period return calculation, which adjusts for external cash flows at the period boundaries, from two methods for handling cash…
This study examines whether LSTM recurrent neural networks can classify the direction of near-term SPY returns from historical daily returns. Its base model uses sequential return inputs, stacked LSTM layers, dropout and batch normalization, and predicts…
This article shows how to simulate ARMA processes in R, inspect autocovariance and autocorrelation behavior, and use those models in a simple equity strategy. It describes using an ARIMA function from an R forecasting library for simulation and plotting…
The document explains a long call butterfly, a defined-risk options position intended for conditions where little movement is expected in the underlying. It combines a long lower-strike call, two short calls at the middle strike, and a long higher-strike…
The article explains standard deviation as the square root of variance and a measure of how dispersed observations are around their mean. It distinguishes population and sample calculations, describing Bessel’s correction for samples, and notes that standard…
This beginner overview explains why foreign exchange exists, how currency systems evolved from barter and gold-backed notes to floating currencies, and how the FX market supports conversion and trading. It describes currency pairs as relative prices,…
The article explains two ways to combine decision trees to address weaknesses such as noise, underfitting, and overfitting. Bagging trains trees independently on bootstrap samples drawn with replacement, then averages regression outputs or uses the majority…
The article lays out a sequence for moving a trading idea toward live use: form a hypothesis, code it, backtest it, test it forward, paper trade, and then consider live trading. It recommends obtaining reliable market data, since missing values and…
This overview introduces Python’s role in quantitative trading, from working with market data and technical indicators to building strategy prototypes, backtests, and supporting risk or execution systems. It describes the language’s open-source scientific…
This tutorial explains how to prepare market data for classification and regression decision trees. It uses daily E-mini S&P 500 futures data and constructs predictors from exponential moving averages, average true range, average directional index, relative…
This project describes a simple web tool for exploring how rule-based trend-following strategies might perform before implementation. Users select a ticker, view closing prices and indicators such as simple moving averages and Bollinger Bands, then define…
This overview describes the spread of algorithmic trading across firms and markets, emphasizing speed, automation, and reduced reliance on manual decisions. It surveys drivers and enabling technologies, including machine learning, artificial intelligence,…
This tutorial explains vector autoregression for modeling multiple time series together. It discusses stationarity checks using augmented Dickey-Fuller tests, differencing nonstationary series, and selecting a common lag order with information criteria.…
This tutorial introduces Bokeh as a Python tool for interactive browser-based plots and dashboards. It distinguishes server-connected plots, whose data can update the interface, from standalone plots, which still support interactions such as linked…