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.
79,386 documents
This document summarizes an introductory treatment of graph neural networks (GNNs), which learn from data represented as entities and their relationships. It explains how convolutional ideas used with images can be generalized to graph structures, whose…
This A-share screening idea combines intraday market activity with a weekly trend condition. It selects stocks with amplitude above 1, current volume above 10,000 lots, a higher opening price, and a weekly five-period moving average crossing above the…
This weekly report examines Bitcoin and Ether options around regulatory news and a busy US macro calendar. It describes short-dated implied volatility rising after enforcement actions, a brief move into backwardation, and a flatter term structure afterward.…
The article reviews the long decline in mutual fund and ETF expense ratios and links it to investor choices, competition, and changes in financial advice and retirement plans. It distinguishes asset-weighted averages, which reflect where investors put their…
This discussion addresses how to use a daily stock popularity ranking obtained through a query interface in a backtest when the research environment returns a dataframe but the backtest environment does not behave the same way. One suggested workflow is to…
This post describes a stock screen restricted to a designated metaverse industry group. Within that group, it selects shares whose average price is above the five-day moving average and whose daily MACD is positive. The stated intent is to combine an…
This Chinese-language post outlines an equity screening idea that combines three signals: rank stocks by relative volume, require the 5-, 10-, and 20-day moving averages to be aligned upward, and look for a 15-minute MACD histogram that is shrinking while…
This example builds a BTCUSDT futures market-making strategy whose fair price is estimated from a spot reference price plus a smoothed spot–futures basis. It resamples spot and futures book-ticker mid-prices, carries observations forward, and calculates a…
The document describes a backtesting feature for BitMEX’s XBTUSD perpetual contract that simulates periodic funding payments using historical funding-rate data. It says the feature is available across JavaScript, C++, and Python, and that event logging can…
The document presents an indicator framework that combines nested swing detection, structural trend changes, Fibonacci retracements, and engulfing candlestick patterns. Short-, intermediate-, and long-term swings are used to identify increasingly significant…
This stock-selection proposal combines a price-range filter, a historical dividend-yield condition, and a turnover-related condition. The stated screen looks for stocks with amplitude above 1%, a 2019 dividend ratio above 25%, and a turnover measure between…
The document describes a support and resistance indicator based on the prior candle’s high, low, and close. For daily levels, it uses the previous day’s candle and applies the resulting levels to charts below the daily timeframe; levels are recalculated each…
This research review summarizes a study of manager changes at Chinese equity funds, distinguishing internal transfers, moves to another public fund, moves to a private fund, and exits from the fund industry. The study compares benchmark-adjusted buy-and-hold…
This stock selection concept combines moderate trading activity, recent price strength, and a technical trigger. It seeks stocks with turnover between 3% and 12%, at least one limit-up event in the preceding 25 days, and a newly formed KDJ golden cross. The…
This Chinese A-share screening idea combines three conditions: MACD above its zero line, share price below 12 yuan, and inclusion on the previous day’s Dragon-Tiger List. The article says screening is intended to run before 10 a.m. on each trading day. It…
This note describes a utility that trails an open position’s stop loss using Parabolic SAR on a selected timeframe. For a buy position, it considers moving the stop when the prior bar’s SAR is above the entry price and below that bar’s low. For a sell…
The document introduces John Ehlers’ Center of Gravity indicator as a finite impulse response filter applied to price, with a configurable calculation period. It presents the indicator as a low-lag tool for spotting potential turning points. The basic signal…
The proposed Chinese equity screen combines three conditions: a recent increase in reported holdings or inflow, a weekly five-period moving average crossing above the ten-period average, and at least two limit-up sessions during the past 500 days. The post…
The document describes a lightweight reporting setup for MetaTrader accounts. An expert advisor writes account balance and position change information to text files, while a separate ICQ bot responds to user commands by sending the contents of selected…
The article explains how to estimate the probability of a binary outcome using Bayesian inference. It uses coin flips to introduce a Bernoulli likelihood for observations and a Beta distribution as a prior for the unknown success probability. Because these…
The document describes a stock screen that selects shares with a prior-day price range above 1%, more than a year since listing, and prior-day turnover above 8%. It explains the intended rationale: range and turnover are treated as signs of activity, while…
The document outlines an expert advisor for EURUSD that trades around the European and American sessions. It identifies session start and end times as configurable inputs and describes a minimum European-session range, stop loss, take profit, and a lot-size…
This document proposes a Chinese stock screen using three signals: a high volume ratio, a rounded price pattern approximated through Bollinger Band contraction or expansion, and at least two limit-up events over 500 days. It describes ranking stocks by…
This document describes a simple screen for Chinese metaverse-related equities. It selects stocks with circulating market capitalization above the stated cutoff and a ten-day price gain that is positive but below a specified upper bound. The accompanying…