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.
8,742 documents
The article presents five principles for short-term stock trading: prominent stocks may attract liquidity despite looking expensive; near-term prices reflect the balance of buying and selling shaped by expectations and sentiment; traders should seek gaps…
The article proposes a short-term equity screen based on amplitude above 1, three consecutive prior daily gains that are not limit-up moves, and large-order net inflow during the afternoon. It interprets amplitude as a sign of an active security and…
This research summary examines Shanghai–Hong Kong and Shenzhen–Hong Kong Stock Connect, comparing northbound and southbound trading and describing the traits associated with northbound holdings. It reports that flows did not reliably anticipate market…
This Chinese equity screen selects stocks with turnover between 3% and 12%, displayed first-level bid volume greater than ask volume, and a weekly five-period moving average crossing above the ten-period average. The note describes these filters as proxies…
This Chinese stock-selection note proposes screening for price amplitude above 1, large-order net-volume readings above 0.05 over at least three consecutive days, and then ranking by fund strength. It presents the combination as a short- to medium-term way…
This document presents a short-term Chinese stock selection rule based on three market activity measures: turnover between 3% and 12%, first-level bid volume greater than ask volume, and a volume ratio between 1.5 and 6. It frames the turnover and order-book…
The document summarizes research on forecasting multiple future steps from limit order book data. Rather than predicting only one future point, the proposed approach uses sequence-to-sequence encoder-decoder networks with attention to generate a path of…
The guide explains how NautilusTrader connects to Bybit for live market data and order execution across spot, linear and inverse contracts, and options. It describes product-specific symbol suffixes, instrument loading, and the differences among mainnet,…
This indicator builds price and volume distributions from lower-timeframe candle data, then displays Value Area High, Point of Control, and Value Area Low. It distinguishes developing levels for the active profile from completed levels for the prior profile,…
This document explains a way to identify binary options symbols among instruments listed in MetaTrader 4’s Market Watch. Broker naming conventions vary: some append a suffix, others use a different marker, and some may follow another pattern. As a result,…
The document describes TradingSlippage as an execution cost applied during backtesting to SMART_LIMIT fills. It says slippage can be supplied at the strategy level, with separate lists for buy and sell orders. This lets a researcher model an assumed cost on…
This note describes a screen for metaverse-related equities using two signals: prior-day actual turnover between 3% and 28%, and large-order net volume above 0.05 for at least three consecutive days. The article interprets the turnover band as evidence of…
This note proposes screening equities for intraday amplitude above 1, prior-day actual turnover between 3% and 28%, and positive net large-order flow during the afternoon. The combined filters aim to find shares showing both price movement and trading…
This recap of an Amberdata and Blockworks webinar discusses institutional participation in Bitcoin markets, with attention to derivatives, market structure, and the possible effects of a spot exchange-traded fund. It frames Bitcoin's 2023 performance and…
The screening rule selects stocks whose codes begin with 60, whose turnover rate falls between 3% and 12%, and whose best-level bid volume exceeds best-level ask volume. The document presents the bid-versus-ask comparison as a way to incorporate liquidity…
The document describes a tick-data compressor that stores changes in bid, ask, and time rather than repeating full tick records. Small price and time changes can fit into a compact representation, while larger differences use additional bytes. It also offers…
This technical reference explains how an order-expiry event is processed in an execution pipeline. The event is applied to the order, updates the cache, and is published on the message bus. It may originate from a venue, a simulated matching engine, or…
This guide explains how to participate in a BigQuant quantitative challenge using A-share minute bars and order-book snapshots to predict future 30-minute VWAP returns. It covers the factor-mining and end-to-end modeling tracks, available templates and data…
The article explains how leveraged perpetual futures positions can be liquidated when traders fail to meet maintenance margin requirements. It treats liquidation data as forced buy or sell order flow that may reveal short-term market pressure, and describes…
This short forum exchange concerns order and trade events that are not appearing inside callbacks in a spread strategy template. The questioner says the template passes those events to the relevant callback methods, but receives no visible output from the…
This podcast recap discusses how AI agents may interact with crypto assets and decentralized applications, alongside a vision for regulated DeFi that connects conventional banking with self-custodied digital assets. The guest describes agents as systems that…
This stock-selection proposal combines three filters: daily amplitude above one percent, a proxy for afternoon large-order net inflow, and a gain below six percent at the 9:25 observation. The stated aim is to find shares with notable movement and buying…
This Chinese A-share screening proposal filters for stocks with an intraday range above 1% during 2021, then keeps observations where price change multiplied by an estimate of very large order flow is positive. The intended interpretation is that volatility…
This proposed Chinese stock screen looks for a daily price range above 1, a ratio between 0.5 and 2 formed from the previous day’s turnover rate and the current auction volume relative to the previous day’s volume, and a current large-order accumulation…