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 article surveys memory management and performance practices for MQL5 applications, particularly Expert Advisors handling frequent events, multiple timeframes, indicators, or large histories. It describes stack and heap allocation, the lifecycles of…
This notebook analyzes reconstructed NASDAQ limit order books to describe intraday spreads and top-of-book depth, then examine whether order-flow imbalance is associated with subsequent bucket returns. It expresses spreads in basis points to compare stocks…
This notebook presents a GT-GAN-inspired generative model for financial series sampled at irregular intervals, such as tick, volume, or dollar bars. Its encoder, generator, discriminator, and decoder use continuous-time Neural ODE dynamics, allowing latent…
This notebook tests Lee-Ready trade classification against aggressor-side labels in Nasdaq order-by-order data. It reconstructs the limit order book from add, modify, cancel, fill, and reset messages, then aligns each trade with the contemporaneous best bid…
This document presents an event-driven method for holding a limited number of intraday positions. Predictions are aligned to price bars using the latest available score, subject to an optional freshness limit. Entry signals use a rolling quantile computed…
This document compares four equity market data sources for studying trades, quotes, and limit order books: AlgoSeek TAQ, Databento market by order, NASDAQ ITCH, and IEX HIST. It explains each source’s granularity, coverage, cost or access conditions, storage…
This chapter presents market data as the result of trading rules, liquidity, and participant behavior. It surveys data from top-of-book quotes through order-level feeds, then describes parsing exchange messages and replaying them into a venue-local limit…
ReinforcedSmoothScalp is a one-minute long-only scalping strategy that seeks frequent entries and small gains. It resamples price to a five-minute interval and uses a 50-period simple moving average there as a broad trend filter. On the trading timeframe,…
Penny jumping is a high-frequency tactic that uses a large visible limit order as a clue to another trader’s intended direction. The example describes a large bid below the best offer: a trader steps one tick ahead of that bid, hoping to sell into the large…
This introductory order flow factor uses a rolling set of recent trades to estimate whether buying or selling pressure is stronger. It compares buy and sell quantities across the full set and a later portion of the sequence, then applies a hyperbolic tangent…
This intraday approach seeks short entries in Bank Nifty when several indicators point downward at once. It checks MACD direction on three timeframes, requires RSI below a stated threshold and ADX above another, and uses a bearish Stochastic relationship…
This document describes a multi-symbol WebSocket template for trading on OKX and Binance. It combines public trade and order-book feeds with private account streams, maintaining local order, position, and balance state so a strategy can react while exchange…
This short-term strategy uses each one-minute candle’s direction as its trading signal. It goes long after a candle closes above its open and short after a candle closes below its open, then closes positions at the following candle’s close. The description…
The strategy combines three MACD configurations with an RSI filter to seek long entries in cryptocurrency markets. It describes averaging MACD signal lines to smooth noise and requiring bullish MACD conditions alongside RSI confirmation.…
This document presents a tick-driven grid strategy that places buy and sell limit orders around the market, then adds to a position as price moves against it. The step between additional orders increases at specified position sizes, while a position…
This cryptocurrency strategy combines several MACD parameter sets into an averaged momentum signal, then uses RSI and candle direction to qualify long entries and exits. Linear-regression-smoothed candles and wick-to-body comparisons are presented as a way…
This strategy uses a 20-period simple moving average as the Bollinger middle band, with upper and lower bands formed using two standard deviations. It treats a close crossing above the middle band as a long signal and describes a cross below as a short…
This short-term mean-reversion system combines Bollinger Bands, a 5-period RSI, and a 50-period volume-weighted moving average (VWMA). Strict long entries require oversold RSI and price below the lower band while remaining above VWMA; strict shorts use the…
The document describes a directional strategy that counts consecutive rising or falling closes and uses those counts to trigger long or short entries. Its overview says the method monitors 1-, 5-, and 15-minute candles to identify bullish or bearish…
This short-term strategy uses the percentage change in consecutive Heikin-Ashi closes to generate directional signals. A rise of at least 0.5% prompts a long entry, while a fall of at least 0.5% prompts a short entry. It opens a position only when the…
This article describes a simple Bitcoin limit-order strategy that estimates prices from cumulative depth in the order book. It scans bid and ask levels until each side reaches a chosen quantity, then places orders slightly inside those levels. If the…
This notebook constructs market microstructure measures from NASDAQ ITCH trade data, aggregates trades into intraday bars, and distinguishes liquidity proxies from order-flow signals and order-book state. It classifies individual trades with a tick rule…
This notebook compares predictive models for ranking NASDAQ-100 stocks by their next 15-minute return using intraday microstructure information such as spreads, depth imbalance, signed volume, and price impact. It selects one representative prediction set…
This notebook describes a GT-GAN-inspired architecture for synthesizing time series with genuinely irregular timestamps, such as tick, volume, or dollar bars. A GRU-ODE encoder maps observations into latent states, while ODE-based generator and discriminator…