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.
5,922 documents
The document raises a portfolio-return calculation question: how to compare long-short stock strategies that hold positions for more than one month. The investor has monthly stock returns and wants to evaluate a shared holding period for the long and short…
The document frames a product-selection problem over multiple weeks. Binary decision variables indicate which products are chosen, while the objective sums production quantities multiplied by prices across weeks. Future prices are unknown, and the question…
The document asks how to model feature–return correlations that fluctuate around zero over time while remaining within the valid correlation range. One proposed construction starts with an unbounded diffusion, such as a mean-reverting Ornstein–Uhlenbeck…
The discussion outlines a historical Value at Risk approach for a portfolio of futures and options. It proposes applying past instrument returns to current positions to estimate historical dollar profit and loss, then selecting a lower-tail percentile as the…
The document explains how to think about carry and roll-down when modeling a bond index. It distinguishes carry, the bond’s return effect under an unchanged yield curve, from roll-down, the part of carry associated with moving along the curve as time passes.…
The document discusses storage architecture for a buy-side firm handling company fundamentals, aggregations, cross-sectional snapshots, and factor research. One contributor advocates storing immutable time-series data in serialized files divided into…
The document raises a question about calculating portfolio variance when portfolio performance is expressed as a logarithmic return. It gives a portfolio log-return expression formed by taking the logarithm of the weighted sum of assets’ exponentiated…
The document asks how to forecast future correlations between securities, contrasting this problem with more familiar volatility and return forecasting. Its brief answer identifies constant conditional correlation as a baseline modeling assumption, as used…
The document explains that Black–Litterman views can come from any researched source of expected excess return. Examples include published forecasts, broker recommendations, machine-learning models, technical analysis that produces target prices, and…
The discussion examines why mean-variance optimization is often called an error maximizer. Estimated expected returns and risk inputs feed into portfolio weights, and small changes in those estimates can produce large changes in the allocations. In the…
The document asks how to turn the leading principal component of asset returns into portfolio weights when its eigenvector contains negative entries. It notes that dividing eigenvector entries by their sum creates weights that sum to one, but this…
The document asks whether linear combinations of two efficient portfolios in a universe of risky assets cover the efficient frontier. One response reports a numerical example in which combinations of two frontier portfolios, including combinations with short…
The document asks how to assess a cointegration-based pairs strategy when trades overlap and remain open for different lengths of time. It questions whether to average trade returns, divide each trade return by its holding days, or compare aggregated trade…
The document addresses how to learn to build project finance spreadsheets, including modeling debt and equity, hurdle rates, internal rates of return, and alternative financing structures. The replies recommend constructing models from scratch so the learner…
The document presents a proposed equity alpha expression built from estimated earnings per share, cash flow per share, estimated sales per share, and estimated dividend per share. It reports using a United States top-stock universe with a one-period delay, a…
The response outlines a simple way to separate stable and volatile portions of non-contractual deposit balances for behavioral analysis. It proposes smoothing daily balances with a moving average to reduce seasonal effects while retaining the underlying…
The document explains how to summarize stock-level correlations by industry group. First, represent each pairwise stock correlation as a row in a long-form table, with fields for date, the industry of each stock, and the correlation value. Grouping by date…
The document examines whether the continuous-outcome Kelly approximation, expressed as mean return divided by return variance, can guide capital allocation across trading strategies. One response distinguishes this approximation from the familiar Kelly…
The document considers how to estimate joint risk for multiple stocks from historical log returns. The proposed workflow computes the variance-covariance matrix, annualizes it, and applies a Cholesky decomposition. The resulting factor can be used to…
The document asks how to estimate the parameters of an asymmetric dynamic conditional correlation model from already standardized residuals, without fitting meaningful univariate GARCH models. The model updates a covariance proxy using lagged residual…
The document explains how to formulate a mean-variance portfolio problem for a quadratic programming solver. To maximize expected return minus a risk penalty based on covariance, the objective must be converted to the solver’s minimization form: use a…
The discussion distinguishes combining expected losses from estimating portfolio risk. If two factor returns have stated expected losses, their combined expected loss is determined by their portfolio weights and the linearity of expectation; correlation does…
The document considers why a fictional company’s share value differs when calculated with the Dividend Discount Model (DDM) and an Earnings Recapitalization Model (ERM). The response argues that the setup is inconsistent if projected dividends exceed the…
The document examines why mean-variance optimization remains influential even though equal-weight portfolios have often performed competitively in empirical comparisons. One explanation is that Markowitz’s framework established the theoretical value of…