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.
16,761 documents
This stock screening proposal combines three conditions: at least five moving averages overlap, a prior-day signal identifies a stock as controlled by large market participants, and the green MACD histogram bars on a 15-minute chart are shrinking. The…
The document describes a support-and-resistance indicator built from the iFractals indicator. Its implementation accounts for the possibility that the most recent fractal value may be redrawn: after the initial calculation, it copies five extra bars beyond…
This document describes an Expert Advisor built around a simple neural network and two indicators: Laguerre_PlusDi and SilverTrend_Signal. Its setup relies on three sequential optimization passes, each activated by setting a Pass parameter and optimizing a…
This research roundup summarizes two studies. The first compares the Fama–French five-factor model with a version that adds momentum, then considers replacing the standard value factor with a more immediate value measure. The summary says the six-factor…
The article explains how a multi-asset daily market-data panel can be turned into model-ready factor and label tables. It separates the workflow into defining train, validation, and test date ranges; adding feature expressions and a future-return label;…
This stock-screening idea combines technical conditions intended to find lower-priced shares with recent upward momentum. It calls for at least five moving averages to converge, a share price below the stated threshold, and at least two limit-up sessions…
This research summary argues that broker stocks deserve separate modeling within CSI 300 enhancement portfolios because the sector has a meaningful index weight and tends to move differently from other industries. It tests stock-selection factors within the…
This trading-system description uses the UltraFatl oscillator’s colored bars to generate signals. A trade is opened at bar close when the indicator changes color among its red or green variations. Positions are exited either through a pending order or when…
This document describes an indicator that overlays Heikin-Ashi style candles on range bars. It calculates a synthetic close from the bar's total price and a synthetic open from the current bar's open and close initially, then from the prior synthetic open…
This Chinese-language competition update reports diagnostics for the ten highest-ranked anonymous factors and tracks a CSI 1000 index-enhancement portfolio. It describes average style exposures estimated through daily multivariate regressions and…
CoensioTrader1 is a multi-currency automated trading system that identifies direction with a daily double exponential moving average (DEMA). It treats three consecutive daily DEMA readings pointing the same way as a trend, then seeks entries in that…
This document describes an automated short-dated options strategy that sells a SPY iron condor late in the trading day, with expiration on the next trading day. It skips a session when the previous VIX close exceeds 25. Otherwise, it selects short put and…
This document introduces two high-frequency trading examples: handling a dataset for reinforcement learning and predicting price trends. It explains that the dataset is represented by a Qlib DatasetH object, which can be serialized to disk and reloaded.…
The document describes a macro allocation framework built from six risk factors covering growth, inflation, rates, credit, foreign exchange, and term spreads. It combines momentum signals with cycle-phase estimates, maps the resulting states into…
This proposed A-share screen combines membership in the metaverse theme with a minimum circulating market capitalization and an enterprise-property condition. The article explains that the last condition is unspecified, so the screen cannot be reproduced as…
This note describes adapting the moving average convergence divergence indicator by using deviation-scaled moving averages in place of ordinary exponential moving averages. Deviation scaling makes the moving average adaptive, following an approach attributed…
This research summary compares monthly factors built from price and volume data with quarterly factors built from financial statements. It reports that market data factors were more often effective in long-short portfolios, and examines their relationship…
This indicator models each price bar as a disturbance whose effect fades over time. It treats bars with Open above Close as rising bubbles and bars with Open below Close as falling drops, then uses the Open–Close difference as the disturbance amplitude. A…
This strategy description applies a simple price rule to one Chinese stock. It defines a reference high as the highest closing price over the past 20 days and a reference low as the lowest closing price over the past 10 days. The stated entry condition is…
This Chinese-language post describes a stock-selection rule combining price amplitude above one, a rounded or arc-like price pattern, and a stock code beginning with 60. It frames amplitude as a way to find more active shares and the arc-shaped condition as…
This Python example implements a Dual Thrust opening range breakout for intraday prices. It aggregates minute data into daily open, close, high, and low values, then calculates a rolling range from prior highs, lows, and closes. At the stated example…
This Expert Advisor uses the Skyscraper_Fix indicator to run separate systems for long and short trades. Inputs prefixed for each direction allow independent settings, including trade identifiers, deposit share, lot mode, and permission to open or close…
This Chinese-language strategy note tests a simple stock screen for mainland China A-shares. It selects companies using three annual-report criteria: net profit growth above a threshold, return on equity above a threshold for three consecutive years, and a…
The document explains the Correlation Trend Indicator (CTI), which compares a price series with an ideal straight trend line using a correlation measure. It describes short- and long-period CTI values as distinct views of trend rather than simply smoothed…