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.
16,761 documents
The document shows how to turn a monthly Treasury bill rate series into a hypothetical value path for an initial investment. It describes carrying the prior month’s value forward and multiplying it by one plus the current rate expressed as a decimal, then…
The document discusses preparing financial data for an LSTM intended to predict index direction or returns. It compares using price levels with returns or differences, and explains that the concern about values exceeding a scaling range reflects both…
The document addresses the challenge of obtaining reliable end-of-day historical prices for Indian equities and calculating returns that are not distorted by corporate actions. It identifies the National Stock Exchange as a source of end-of-day and intraday…
The document asks how to obtain the first three moments of simulated aggregate losses and whether to use sample averages or formulas from the collective risk model. The answer distinguishes two routes: if the frequency and severity distributions are known,…
The document presents possible master’s thesis directions in option pricing, aimed at a beginner seeking a manageable empirical or model-comparison project. One suggestion is to fit a GARCH volatility model to market data, use it in Monte Carlo option…
The document explains why matching Reuters Instrument Codes (RICs) to Compustat tickers across historical datasets can be unreliable. Ticker-like identifiers may differ for share classes, as illustrated by examples where Reuters and Compustat use different…
The document considers how to choose among many Kelly-based betting strategies after testing a UFC fight prediction model. The model outputs win probabilities, and the user evaluates parameter combinations using bookmaker odds, return on investment, and…
The document outlines a simulation procedure for a multivariate DCC-GARCH(1,1) model. First, simulate each series’ univariate GARCH volatility and returns, then standardize returns to obtain residuals. Use those residuals to update the DCC latent covariance…
The document explains ways to simulate a three-dimensional linear stochastic differential equation with vector drift, a matrix multiplying the state, and a matrix diffusion driven by a higher-dimensional Brownian motion. It describes expressing each drift…
The document explains how to estimate expected shortfall (ES), also called conditional value at risk, with a GARCH volatility model. It separates returns into a conditional mean, conditional volatility, and standardized residuals. ES for the standardized…
The document considers how to test whether an arbitrary daily time series predicts a stock’s future movement. The proposed workflow is to split observations into training and test sets, difference both series to work with changes, and examine correlations…
The answer explains how to continue a fitted GARCH(1,1) volatility series when historical data is unavailable. Keep the previously estimated parameters fixed, then initialize the recursion with the most recent residual and conditional volatility estimate.…
The document asks how a backtest should model early exercise when short an American option. It contrasts using an arbitrary threshold for exercise with treating the contract like a European option, then describes exercise considerations that depend on option…
The document asks for reference material to help build a backtesting system that models futures and equities realistically. It highlights the need to account for buying power, profit and loss, and margin, including the different conventions that apply to…
The document asks how to calculate the t-statistic for the difference between low-beta and high-beta portfolio alphas in an analysis of the beta anomaly. The accepted answer describes forming a time series of portfolio returns by subtracting one portfolio’s…
The document considers whether machine learning can produce several plausible future price paths from historical closing-price behavior, for planning trade adjustments. The answer describes the task as supervised learning: define and label outcome classes…
The document discusses how to organize daily stock prices and company financial statements in a database for screening and backtesting. Its main recommendation is to model instruments, trading venues, price observations, and companies as related entities, so…
The document raises a modeling question from a course example that uses principal component and factor analysis to predict stock prices. It reports the course author’s claim that regression should use returns rather than price levels, linking that…
The document describes a proposed way to evaluate a multi-asset portfolio using weekly returns and a time-varying matrix of portfolio weights. The intended test samples start dates, measures performance over a one-year period, rebalances at regular…
The discussion compares R with C++ and Python for quantitative research, data analysis, and production software. Contributors describe R as productive for exploratory analysis, statistical modeling, visualization, and working with established packages. They…
The question describes a trade list with tickers, buy dates, and sell dates, and asks how to evaluate its performance when each stock receives equal weight. The response points to Backtrader as a Python library for building and running backtests. It offers a…
The discussion addresses how to reconstruct historical equity ticker changes when a ready-made long history is unavailable. One proposed method is to use daily security data containing both ticker symbols and SEDOL identifiers. Since the identifier usually…
The document shows how to backtest a portfolio of ETFs using inverse-volatility weights estimated from recent returns. A target-weight function obtains closing prices for the preceding 20 trading days, computes returns, estimates each asset’s volatility, and…
This discussion outlines vendor and dataset considerations for researchers seeking historical US equity fundamentals. The requested features include broad export rights, coverage of firms that later disappeared through bankruptcy or mergers, financial…