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.
1,116 documents
The document discusses ways to detect hidden liquidity in a limit order book. One proposed signal is repeated trading at a best bid or ask while displayed size is replenished, or while the price repeatedly returns to the same level despite continuing buying…
The document surveys strategies in which receiving market data or reaching an exchange sooner may affect execution. It describes latency arbitrage as a contest over speed, with examples including arbitrage across fragmented equity venues, triangular…
The document outlines a progression of methods for testing strategies that depend on timely execution, especially passive orders and cross-market hedging. For liquidity-taking strategies, top-of-book data may support conservative size assumptions that can…
Quote spam, also called quote stuffing or book colouring, refers to order activity that changes the visible order book without reflecting a genuine intention to trade the displayed quantity. Because participants use order-book depth and prices to assess…
The document explains how to turn irregular stock trade ticks into a regular time series using previous-tick interpolation. One approach converts epoch milliseconds to POSIX time, creates a five-minute grid, and uses interval lookup to select the latest…
The document examines unusually distant, persistent quote levels in one day of AAPL TAQ data. The accepted explanation links the venues shown to inverted pricing, where makers pay fees and takers receive rebates, and attributes the observed gaps to temporary…
The document compares direct exchange connections with a consolidated market data vendor for someone seeking daily data and possibly delayed or real-time tick data. It explains that direct feeds require building and maintaining exchange-specific handlers,…
The document distinguishes market-by-order (MBO) data from market-by-price (MBP) data. MBO records individual orders, while MBP aggregates displayed quantities by price. Exchanges maintain order-level books internally, but traders build the representation…
The document compares keeping strategy research and live trading in one environment with translating the strategy into a separate implementation language. It explains that research often analyzes fixed datasets with vectorized calculations, while live…
The document examines why maximum-likelihood estimates for an exponential Hawkes process can drive the decay rate and excitation parameter toward very large values when tick records share millisecond timestamps. In the stated likelihood recursion, zero…
The document compares two ways to connect an Interactive Brokers tick feed to analytics and signal generation: a single integrated application that keeps data in memory and writes it to disk, or separate processes that persist feed data for independent…
The document considers how high-frequency market making works when short selling is restricted. It explains two ways a participant may still provide ask-side quotes: an official market maker may receive a short-selling waiver, or another participant may…
The document discusses how to simulate trade prices that behave like a random walk. One answer recommends modeling the bid-ask spread and using Poisson or Hawkes point processes for order arrivals and cancellations. A price move can occur when the queue at…
The document surveys several free or low-cost sources mentioned for historical market data. Its main example is an undocumented onvista interface for retrieving stock tick data by security identifier, exchange, and trading day. The author describes how a…
The document considers whether an equities focused algorithmic firm could earn very high annual returns, including a claim of 100% returns from event driven trading and text mining. Its responses say such outcomes may be possible but emphasize that returns…
The document distinguishes financial bars from statistical resampling methods. Time bars divide observations by clock intervals, while tick, volume, and dollar bars aggregate irregular transaction data until a chosen trade count, traded volume, or traded…
The answer considers whether banks and asset managers are likely to develop trading algorithms in-house or rely on specialist firms. It argues that either path may be difficult within traditional institutions, citing gaps in management’s quantitative…
The document weighs R and Python for quantitative finance tasks, including time-series data handling, statistical modeling, mathematical computation, visualization, derivatives pricing, system integration, and deep learning. Its answers describe different…
The document asks how to adapt the two-scale realized variance estimator (TSRV) associated with high-frequency data. It proposes calculating realized variance at two subsampling intervals, then subtracting the shorter-scale estimate from the longer-scale…
The document raises a comparison between a Fourier-based estimator of realized variance and covariance and the conventional sum of squared returns. The author applies the estimator to one day of ultra-high-frequency observations, samples the data at…
The document distinguishes Avellaneda–Stoikov quote placement from the choice of order quantity. The model’s quoted prices respond to inventory and other model inputs, while its trade units are relative: scaling every unit by the same factor does not change…
The document raises a practical issue in constructing an implied volatility curve for ETF options during high-frequency intraday trading. Its premise is that option quotes may update faster than the ETF cash price, so calculating implied volatility from the…
The document explains what trading servers colocated at an exchange can receive and how they may subscribe to those feeds. Exchange data is commonly distributed over fibre using multicast, with subscriptions selectable by feed group or partition; TCP feeds…
FIX repeating groups encode array-like collections of related fields within a single message. A count field announces how many entries follow, and the group structure lets a recipient interpret repeated values as separate entries. For example, a message can…