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 response addresses how to compare option-pricing models when their Greeks imply different hedge positions. It points to empirical studies that evaluate alternative pricing models and implied-volatility functions, using delta hedging of equity options as…
The document asks why a five-year stock-price chart contains frequent, brief spikes. The answer attributes them to missing observations in the displayed data: according to the response, the data provider represents unavailable prices as zero. When a chart…
The document raises a data-quality question about using hourly OHLC prices for a cryptocurrency in strategy research. Its supplied dataset carries more decimal places than the values displayed by a chart, and the author asks whether to round the historical…
The answer explains that a 1:2 risk–reward ratio is a convention rather than a universally correct rule. It offers two possible reasons traders favor it: loss aversion may lead investors to seek more potential gain than potential loss, and a reward-to-risk…
The document addresses how to identify past changes in futures contract tick sizes, which matter when interpreting historical price data and trading costs. Its practical suggestion is to search exchange press releases, where exchanges announce contract…
The discussion compares arithmetic and geometric approaches to the Sharpe ratio and emphasizes that they answer different questions. The conventional arithmetic version uses average excess simple returns relative to their standard deviation and is often…
The document compares simulating an asset price directly with simulating its logarithm under geometric Brownian motion. Applying Itô’s lemma gives log price a constant drift adjusted downward by half the variance and a volatility-scaled Wiener process. The…
The document outlines architectural decisions for building a customizable Python backtesting engine. It highlights market-data storage and serialization, memory limits, handling unstructured feeds, durable output storage, and access to prior run results. It…
The document compares storage approaches for real-time and historical market data, focusing on column-oriented databases, row stores, in-memory arrays, flat files, and time-series systems. Column stores can speed analytical reads by scanning selected columns…
The document compares a drawdown survival formula attributed to John Wolberg with results from two research papers on drawdowns. Wolberg’s expression gives the probability of a drawdown at least as large as a specified percentage, using the drift and…
The document discusses ways to reduce the time needed for repeated strategy backtests. It suggests identifying the data the strategy actually uses and maintaining a buffer of relevant observations as new events arrive. For computationally intensive logic, it…
The document explains why Monte Carlo estimates of a European option price can become less precise as volatility rises. The central point is that the estimate averages simulated payoffs, and its sampling error depends on payoff variance and the number of…
The document asks how to replace close prices with bid and ask prices in a VectorBT signal backtest. Using separate bid and ask observations can represent trade-side prices more realistically than a single close, but the answer says that a convenient…
The document asks how to estimate the variance of a stratified Monte Carlo estimator using each stratum’s sample sum and sum of squared observations. It compares a variance expression involving stratum probabilities and variances with an algorithm that…
The document asks whether Monte Carlo option-pricing results from different copula models can be compared when antithetic variates are used only for symmetric copula families. The concern is that the variance-reduction technique may not be applicable to…
The document clarifies that a Sharpe ratio calculated from daily returns is a daily estimate, regardless of how many observations were used, and that converting it to a monthly or annual figure depends on the return interval. Under the usual…
The document distinguishes the return of an underlying asset from the return series generated by a trading strategy. An asset’s daily price changes describe its buy-and-hold performance, while a strategy’s wealth changes describe the performance an investor…
The document surveys algorithmic trading platforms and tools, including hosted research environments, open-source backtesting engines, and locally assembled development stacks. It describes Quantopian and Zipline as Python-centered research and backtesting…
This discussion examines a simulation inspired by Mark Spitznagel’s account of traders choosing between strategies with different payoff shapes. One strategy offers frequent small gains and rare large losses; the other offers frequent small losses and rare…
The document outlines a proposed automated foreign-exchange strategy built around cointegration and forecasting a spread. Its listed workflow transforms price data into log returns, treats outliers, performs linear regression, tests for cointegration with an…
The document discusses how to encode intraday trading rules in a genetic algorithm when signals are mostly Boolean conditions. One reply proposes representing entry and exit logic as separate chromosome segments, with genes selecting AND or OR operators…
The document surveys empirical approaches for assessing how stock market efficiency changes over time, distinguishing broad market measures from firm-level analysis. For firm-specific questions, it identifies event studies as a common procedure and points to…
The discussion presents several ways to choose autoregressive and moving-average orders for an ARMA model. ACF and PACF patterns can suggest whether the series has an AR or MA component: an MA process tends to show a cutoff in the ACF, while an AR process…
The document asks how to choose the degrees of freedom for t-tests of mean cumulative abnormal returns (CAR) and mean buy-and-hold abnormal returns (BHAR) across a sample of firms. It gives test-statistic forms that divide each sample mean by its…