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.
9,660 documents
The document frames predatory trading as a contest between a trader attempting to force liquidation and a targeted trader who may be solvent and able to draw on reserves or credit to maintain a position. It contrasts this situation with models centered on…
The document explains that a useful forecast target depends on the market-taking task. For a large order, a short-horizon mid-price forecast can help time execution. For a simple single-exchange strategy, the relevant question is whether prices will cross…
The document explores how to build a trading system from traditional chart patterns and machine learning. It raises choices about classification targets, whether patterns should be labels or inputs, and whether a model can identify patterns directly from…
The document explains why Level II equity market data does not have one universal update schedule. The cadence depends on the exchange and the particular data product. Some feeds publish aggregated book information on a fixed interval, while many products…
The discussion asks how to choose the number of historical candles used to estimate a spread z-score in a crypto perpetual swap pairs strategy. The question notes that different pairs appear to perform best with different window lengths in both backtests and…
The document explores modifying a depth-weighted midpoint so that distant quotes with little chance of execution contribute less. The proposed approach is to weight bid and ask levels by the probability that prices reach those levels, estimated from…
The document describes a liquidity-risk measure for a long-only equity portfolio: estimate how many days it would take to sell each holding. Under ordinary conditions, the measure can use average daily volume and an assumed participation rate. To represent…
A one-year-forward 2-year versus 5-year Treasury steepener can be built from bonds with settlement in one year or expressed through forward-starting interest rate swaps. For bonds, the examples construct forward exposures by combining securities that mature…
This exchange addresses a market data session that stopped receiving snapshots after a broker reported missing client heartbeats. The key diagnostic is that client heartbeats and server initiated test requests are distinct messages with different expected…
The discussion challenges the inference that widespread retail losses show short term prices are predictable. A trader’s profitability depends on more than whether prices move up or down: transaction costs such as spreads and commissions can create negative…
The document examines a proposed foreign exchange carry trade based on differences between brokers that accrue rollover interest continuously and those that apply it at a daily cutoff. The proposed trade briefly holds a high-yield currency position through…
The document explains why a self-financing trading strategy is modeled as predictable, or previsible, while asset prices and portfolio value remain adapted. The key timing idea is that holdings for the next interval must be chosen using information available…
The document explains how a binary strategy signal becomes a sequence of trading orders in a simple moving-average backtest. The signal represents the desired position: zero means holding no shares, while one means holding a share. Taking the signal's first…
The document describes a forex market-making bot that places offers around the mid price and refreshes them at regular intervals. In the market described, thin order books can cause sharp mid-price jumps after a large order; the moves are said to last…
The document clarifies the meaning of an intermarket sweep order (ISO) in the context of U.S. equity market rules. It distinguishes an ISO from an order that is automatically routed to other venues when it encounters better displayed prices. Instead,…
The document explains how German-style leveraged certificates with a stop-loss knockout relate to products known as turbo warrants. The answer groups these instruments with mini futures and notes that issuers may use labels such as turbo certificates, short…
Level 1 market data shows the best bid and ask, their displayed sizes, and sometimes the latest trade price and size. The document explains why changes in displayed bid or ask quantities cannot be treated as traded volume: a size change may reflect…
The document explains why a trader might choose a contract for difference rather than buy shares directly. A CFD provides exposure to changes in an underlying stock’s price without ownership of the stock. Because the trader posts margin rather than paying…
The document considers how to simulate an order book for testing strategies that submit market and limit orders. It recommends beginning with a simplifying assumption: the simulated strategy’s orders are small enough not to alter the price path. This can…
The discussion examines whether top-of-book queue sizes help predict the direction and timing of the next price move. The questioner implements a Markovian limit order book model and finds that empirical probabilities conditioned on bid and ask size are…
The document asks what defines a package trade in rates markets, whether a package must be DV01-neutral, why hedge funds request one, and why it may be hard to price. Its example is a set of instruments traded together to target exposure around a particular…
The document explains the Roll model, which estimates the bid-ask spread from the negative autocovariance of consecutive high-frequency price changes. The negative relationship arises when trades alternate between the bid and ask: transaction prices move…
The document explains that novating a non-deliverable forward does not necessarily change its risk-free forward mark to market. The effect depends on how the trading desk separates the contract’s market value from adjustments for counterparty exposure,…
The document explores whether some constraints in high-frequency trading apply broadly, even to firms with substantial spending on hardware, software, and co-location. The response discusses data-center scale, venue fees, processor hardware, co-location, and…