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 asks how to build two structured matrices whose entries decay with the distance between time indices: one uses exponential decay controlled by a positive scale parameter, and the other uses powers of a coefficient whose magnitude is below one. A…
The document discusses whether time-series features must be weakly stationary for neural networks, other predictive machine learning models, or clustering. It argues that nonstationary predictive inputs can encourage a model to rely mainly on…
The document describes how to turn simulated uniform observations from a fitted copula into return innovations compatible with previously fitted AR-GARCH models. The proposed step is to apply the inverse cumulative distribution function of the conditional…
The document explains why randomly dividing financial observations into training and test sets can create look-ahead leakage. Its example uses daily returns for S&P 500 stocks modeled with market beta. If the full sample includes a persistent market rise or…
The discussion asks whether tuning a trading model across bootstrapped versions of historical returns can reduce overfitting to one observed market path. It outlines dependent bootstrap approaches that preserve time-series structure, including resampling…
The document is a request for alternatives to maximum likelihood estimation and regression when calibrating parameters of a stochastic differential equation. The questioner reports practical difficulty maintaining an SDE calibrated through those approaches…
The document raises the problem of using regression splines when new predictor values fall outside the range covered by calibration data. Its example is electricity load forecasting: a model trained on winter temperatures may be used as spring temperatures…
The document considers clustering a large stock universe using both return correlations and company characteristics such as valuation and size. Correlation-based distances can group stocks that move in similar directions, while feature-based clustering…
The document surveys ways to assess whether a time series is stationary, starting from a question about confirming a KPSS result. Suggested methods include the Augmented Dickey–Fuller, Elliott–Rothenberg–Stock, Phillips–Perron, Schmidt–Phillips, and…
The document outlines a model validation workflow and points readers toward regulatory guidance, books, and research on model risk. Its practical sequence begins with conceptual soundness: independently derive or review the model’s mathematics, identify…
The document describes a practical limitation of Empirical Mode Decomposition (EMD) for streaming financial time series. When new observations arrive and the decomposition is recomputed, the number and values of the intrinsic mode functions can change. The…
The document presents an example of estimating time-varying betas between several exchange-traded funds with a state-space model and Kalman filtering. It describes preparing adjusted price-change data, fitting a separate regression for each ordered pair of…
The document describes a forecasting problem involving several public equity indices observed quarterly, with a requested horizon of at least fifteen to twenty samples. It reports that a VAR or VARMA specification fitted the historical data well but…
The document discusses building an affinity matrix to cluster stocks, with the aim of studying cohesion within and between ETFs and possibly supporting arbitrage research or risk modeling. It compares clustering on summary statistics such as average return…
The document discusses generating Student-t random variates for use as innovations in a Brownian motion or geometric Brownian motion simulation. It notes that statistical software can generate these variates and gives examples of programming environments and…
The document compares jump diffusion models and neural networks, especially LSTMs, for forecasting time series such as stock prices or ATM cash withdrawals. It distinguishes forecasting conditional averages from modeling the distribution of future outcomes.…
The document asks how to prepare daily predictive datasets when features arrive at different frequencies. Its example combines infrequent company earnings information with more frequent variables to predict a daily outcome. Because quarterly events leave…
The answer describes a trading approach for returns generated by a known two-state Gaussian hidden Markov model. Rather than infer regimes from moving averages or other heuristic indicators, it recommends updating the probability of each hidden state from…
The document is a request for guidance reproducing results from a study of the Great Recession using Markov-switching vector autoregression and Markov-switching dynamic stochastic general equilibrium models. It identifies an archived R package that can fit…
The document discusses how the number of trees and the number of predictors may affect random forest performance. Because forests use bootstrap samples of observations and random subsets of features, too few trees may leave some observations with little or…
The document examines differential Sharpe and downside deviation ratios (DSR and D3R), which use exponentially weighted estimates of returns and their squares to update risk-adjusted performance measures incrementally. This can avoid recalculating a…
The discussion considers building a neural network to generate buy, sell, or hold signals from stock prices and technical indicators such as RSI and Williams %R. The response recommends defining a prediction horizon and labeling the direction of returns over…
The document asks how to estimate outcomes for US men and US women from three separate height datasets: people in the US, men worldwide, and women worldwide. Each dataset has its own linear regression, and some predictors may overlap. The proposed approach…
The document explains ways to generate scenarios whose features retain specified marginal distributions or ranges while exhibiting dependence. It warns that applying a Cholesky factor directly to bounded, non-normal variables generally changes their marginal…