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.
168 documents
The document discusses practical uses of equity return factors such as the Fama–French factors, momentum, and liquidity or tail-risk measures. It describes factor investing as a portfolio construction approach and notes that predicting factor returns, often…
The document explains how to estimate coefficients in a regression whose intercept and slope depend on a binary state indicator. The proposed method splits observations according to the indicator’s lagged value and fits the same regression separately to each…
The note asks whether traditional factor models become less adequate as markets grow more complex and new return patterns emerge. It cites the Fama-French three-factor model, which captures broad cross-sectional return patterns in the mid-1990s but does not…
This discussion explains how to interpret a time-varying leverage multiplier in a winner-minus-loser momentum strategy. The multiplier scales both sides of the portfolio: for a given amount of capital, the long positions in winners and short positions in…
The document discusses a log-log regression method for estimating the Hurst exponent from a price series. For each lag, it calculates differences between log prices separated by that lag, measures their variance or a related dispersion statistic, and fits a…
The document describes a planned empirical study of cross-sectional stock momentum using OSEAX constituents over a historical sample. Its proposed strategy ranks assets by past performance over a selected horizon, buys the strongest group, and shorts the…
The document considers whether ESG can be added as a factor to the Fama–French five-factor model and how such an extension should be interpreted. It distinguishes a factor that captures exposure to priced cash-flow risk from a preference for firms with…
The document discusses choosing block lengths when resampling returns to simulate long investment horizons for portfolio allocation analysis. Its main principle is to choose a length that preserves dependence patterns relevant to the portfolio, including…
The document offers a reading guide for someone moving from foundational portfolio theory toward practical portfolio management. It starts with Markowitz’s portfolio selection work and Sharpe’s capital asset pricing model, then points to research on Bayesian…
The document responds to an observation that volatile Bitcoin prices seem to form a Weierstrass-like pattern across candlestick time scales. It explains that rough, fractal-like paths are not unique to cryptocurrency: Brownian motion and related stochastic…
The document asks how to incorporate company size when constructing the Fama-French winner-minus-loser (WML) equity factor. It notes that winner and loser groups are formed using cumulative returns over the period from month t-12 to t-2, then raises a timing…
The document weighs whether investors should include commodities in diversified portfolios. It presents arguments on both sides, noting that asset-allocation products and some institutional portfolios use commodity exposure, while the cited research is not…
The document clarifies broad job terminology for research into fixed-income investment strategies. Index strategies aim to track a benchmark passively, while alpha strategies use an active systematic approach intended to outperform that benchmark. Momentum…
The document asks how broadly to define mean-reversion and momentum strategies, including whether they correspond to particular latent-variable dynamics or more general properties of price processes. The accepted response gives informal meanings: mean…
The document asks how to model prices that are pulled toward a target value but may overshoot it when momentum persists. It presents a discrete return regression with both a lagged-return term and a target-gap term, then reviews possible continuous-time…
The document considers how to calculate stock price momentum from weekly observations and whether short lookbacks, such as several weeks, are standard. It presents a simple measure based on the difference between the current closing price and the close a…
The question considers forecasting a future multi-day return from a history of rolling returns. Because adjacent rolling windows share most of their daily observations, the inputs are strongly autocorrelated. The response says that autocorrelation alone does…
The document asks how to define a stock that fades through the day in a way that can be measured. An open-to-close decline alone may miss a rise earlier in the session followed by a sharp late drop. The questioner suggests requiring an early high of day that…
The document asks why a one-year Bitcoin futures contract can trade at a premium whose annualized rate exceeds a comparable government bond yield, despite standard cost-of-carry relationships. It considers whether demand for leveraged exposure may help…
The document presents a replication attempt comparing price momentum with two earnings-based momentum signals, standardized unexpected earnings (SUE) and earnings announcement returns (CAR3). The researcher describes building SUE from quarterly earnings per…
The document asks how to interpret cross-asset moves after an FOMC announcement and whether deleveraging can be measured through changing covariance, signal responses, or trend formation. The response cautions against explaining market moves with a single…
The document considers which market variables might be studied alongside Twitter activity, including index and stock prices, price differences, trends, and expected returns. A response recommends treating posts as a source of market sentiment rather than…
The document asks why Jegadeesh and Titman used overlapping portfolio holding periods when testing momentum strategies. The replies give two intuitions: overlapping periods can create a larger sample than non-overlapping periods, and examining portfolios…
The document considers whether publishing a technical indicator can reduce its subsequent trading performance. It frames a strategy’s historical results as a mix of genuine alpha and overfitting, with only genuine alpha expected to persist out of sample;…