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 considers how to recover a limit order book after a process or machine failure. The proposed approach in the question is to save the full book state periodically, while the reply focuses on persisting the event stream so the system can rebuild…
The document surveys ways to estimate the direction and size of upcoming order flow from intraday market data. It distinguishes behavioral models, which simulate trader actions, from statistical approaches that use tick-level order book variables and other…
The document introduces autoregressive conditional duration models in the context of high-frequency financial data. The questioner has implemented an ACD model in R using trade-only observations and asks how modeling elapsed time between trades, or volume…
The document suggests three input features for training a binary classifier to predict bid or ask price movement from high-frequency order book and trade data: bid-ask spread, bid-ask volume imbalance, and signed transaction volume. Signed volume is positive…
The document describes how a trading system can recover market-data messages lost while receiving a low-latency multicast feed. Because multicast commonly uses UDP, packets can be dropped, leaving a client’s order book incomplete unless it detects and…
The document reviews evidence on whether high-frequency trading changes market quality in ordinary conditions and during stress. It points to research concluding that greater low-latency activity improves short-term volatility, spreads, and displayed…
The document examines why a reproduction of an older study’s positive, exponentially decaying autocorrelation in S&P 500 log returns does not appear in more recent minute data. The answer says that current high-frequency equity returns commonly show negative…
The document considers whether a fault at one exchange could create inconsistent trade records or apparent duplicate share sales, then discusses how exchanges and their supporting systems seek to preserve transaction integrity. The response uses the database…
The document explores how to backtest an Avellaneda–Stoikov style market-making strategy using historical limit order book data. The question describes estimating order-arrival intensities from synchronized order and book events, then asks how simulated…
The document discusses whether familiar time-series indicators such as MACD and RSI are useful as entry or exit signals in high-frequency trading. One response distinguishes visually interpreted technical analysis from quantitative finance, which generally…
The document discusses what mathematical preparation high-frequency trading may require. One answer emphasizes applied tools such as linear algebra, statistics, time-series analysis, optimization, and sometimes machine learning, while noting that practical…
The document describes a strategy using 30-second bars on E-mini S&P 500 futures that performed well in backtests and walk-forward tests but lost in live simulation because small execution-price differences erased its edge. The question asks whether…
The document explains the practical limits of timestamp precision in stock market data, distinguishing timestamp resolution from the frequency of actual trades and quote updates. Nanosecond timestamps are used by specialized data providers and can help order…
This answer distinguishes designing execution methods from monitoring individual trades. It argues that quants can analyze strategies, test them, and work with programmers to implement execution algorithms, while traders or managers typically oversee live…
The document describes a workflow for obtaining stock price data, turning timestamped records into a Pandas DataFrame, and saving the results. The intended application is to compare American depositary receipts with their ordinary-share counterparts,…
The document questions whether a nearby-versus-next-month futures spread is a stable mean-reverting series suitable for high-frequency arbitrage. It challenges the assumption that the spread should track an interest-rate benchmark, explaining that futures…
The document describes pinging: sending small orders into a market to infer whether larger resting orders may be present. A quick fill is presented as a possible signal that deeper liquidity is behind the displayed or encountered order. The original question…
The document discusses fitting the arrival-rate parameters in the Avellaneda–Stoikov market-making model when observed fill rates do not appear exponential in spread. The author compares empirical spread buckets with candidate curves, including a…
The document discusses whether FIX Simple Binary Encoding can reduce the development effort or bandwidth costs of high-frequency trading connections compared with proprietary exchange protocols. One response stresses that firms generally must use the…
The discussion explains why a high-frequency backtest’s latency assumption should reflect both message timing and the strategy’s sensitivity to event ordering. For spread-crossing or arbitrage strategies, it suggests modeling latency as variable, potentially…
The discussion asks whether trade and order-book data can reveal when a large order was split into smaller executions. It distinguishes identifying one participant’s activity from grouping executions caused by a single marketable order. Order identifiers do…
This discussion collects risk management topics relevant to automated trading, with particular attention to high-frequency systems. It names drawdowns, runs of losses, empirical loss distributions, confidence intervals, value at risk, slippage, liquidity,…
The document considers how to simulate a passive buy order using trade prints and snapshots of the best bid and ask, while assuming the simulated order has no market impact. The proposed simple approach is to use changes in bid and ask prices as a rough…
The document raises a conceptual question about how quantitative and algorithmic trading firms can seek returns if asset prices follow random walks. It also asks whether random-walk behavior would undermine models of limit order books, using research that…