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
The document considers a geometric Brownian motion whose drift itself follows a mean-reverting stochastic process. It highlights an identification challenge: observed changes in the price process may come from changing drift or from the price process's own…
The document explains how to set up supervised learning targets for predicting a stock’s closing price at several future dates. It uses lagged open and close prices as input features, then assigns the close price one, three, and five periods ahead to…
The discussion distinguishes modeling order book dynamics from implementing a matching engine. It introduces the Queue Reactive model as a way to simulate a limit order book: trade, insertion, and cancellation events at each price queue occur with…
The document presents methods for forecasting revenue from subscriptions that can be canceled at any time. Revenue in a future period comes from both existing subscribers who remain active and new customers, so a simple forecast of total historical revenue…
The document raises a practical question about connecting statistical techniques learned in isolation to investment and trading work. It asks for examples that show the reasoning behind turning analysis into a model or strategy and implementing it, without…
The document surveys places to find quantitative finance research, distinguishing practitioner publications, academic journals, working paper repositories, and conferences. It mentions broad repositories such as arXiv and SSRN, specialist quantitative…
The document compares Python and MATLAB as starting languages for quantitative finance, with additional views on R and Julia. One answer favors Python for its open source ecosystem, broad community, general-purpose uses, and extensive libraries, while noting…
The document compares structural breaks, changepoints, and regimes in time series. A structural break is framed as a change in a population regression relationship, which may occur abruptly or evolve gradually. Changepoint methods instead seek whether and…
The document examines why Monte Carlo option prices can differ when stock returns are simulated with a normal inverse Gaussian (NIG) distribution estimated from historical data. In the example, the NIG simulation produces a higher call value than both a…
The discussion asks whether a general market model could predict how long a trading strategy’s alpha will persist. It presents several perspectives: asset-pricing models can relate expected returns to risk factors, while evolutionary economics frames…
The document asks how to label minute-by-minute stock price changes when the current and future closing prices can be equal. Its proposed setup assigns two classes for rises and falls, then considers adding a third class for no change. The practical issue is…
The discussion concerns fractional differencing as a way to balance stationarity with retention of information in time series used for supervised prediction. The question asks whether predictions from fractionally differenced data should be reintegrated into…
The document explains several reasons a quantitative trading strategy may restrict itself to liquid, publicly traded assets that can be modeled. Low transaction costs matter when expected profits come from small pricing anomalies: trading costs can erase…
The document is a literature guide for studying Bayesian methods in portfolio management. It responds to a reader who finds the mathematical treatment in an early Bayesian regression paper difficult and is looking for a suitable learning path, especially one…
The document sketches a data-driven workflow for developing systematic trading ideas: identify possible market regimes, find predictors from price or fundamental data, combine weaker signals with machine learning or ensembles, and refine rules through…
The document outlines topics that may help someone entering a bank internship focused on evaluating or building risk models. It distinguishes market risk from credit risk and points to different regulatory and analytical foundations for each. For market…
The document explains why a copula model for financial time series is often applied to standardized residuals after fitting a univariate ARMA or GARCH model, rather than directly to raw observations. Raw series may contain serial correlation and changing…
The document asks for an advanced statistics resource suited to someone with graduate-level mathematics and probability who is preparing for hedge fund interviews. The requester values proofs and computational exercises. Replies recommend books spanning…
The discussion challenges a simple rule that declares a mortgage defaulted once a threshold share of payments is missed. A missed payment may be cured, and payment behavior can change as the borrower’s circumstances and macroeconomic conditions evolve.…
The document explains a two-stage approach to neural-network calibration of the Heston stochastic-volatility model. First, a network learns the mapping from model parameters to an implied-volatility grid. To create training examples, implied volatilities are…
The document reviews a strategy-selection pipeline that fits models on training data, tunes hyperparameters using validation-period simulated profit and loss, selects top-performing instruments or strategies, and evaluates the resulting portfolio on a…
The document clarifies a passage about estimating whether a security’s observed returns are compatible with a specified data-generating process, or DGP. The answer frames this as comparing empirical properties with a chosen parametric model to gauge…
The document examines why an option pricing model that performs well in one historical period may perform poorly in another. It proposes grouping contracts dynamically from past pricing errors, then using machine learning to forecast next-week errors from a…
The document discusses how to choose the smoothing factor, alpha, for exponential smoothing used to preprocess trading data before a machine learning model. It gives a rule linking alpha to the sampling interval and a chosen time constant: a shorter time…