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 guide explains the workflow for a BigQuant contest focused on constructing 15-minute factors from three-second stock snapshot data. Participants are asked to write factor logic without using model-generated factor synthesis. The platform provides…
This trading system enters when a colored arrow from the Chandelier Exit indicator appears at bar close. It follows the indicator’s trend signal and can increase the volume of an open position when the latest deal’s profit exceeds a user-set threshold. The…
This Qlib configuration trains an ADD model using a GRU base model and Alpha360 features to rank CSI 300 stocks. Features are robustly normalized and missing values are filled; labels are cross-sectionally rank-normalized after missing labels are dropped.…
This expert advisor trades changes in the cloud color of a Stochastic Chaikin Volatility indicator. It checks for a change when a bar closes and uses that event to form a trading signal. The document describes the signal rule but does not explain the…
This Expert Advisor uses the wlxBWWiseMan-2 semaphore indicator. It generates a trade signal at bar close when a graphical object in the corresponding signal color appears. The document also notes that the compiled indicator must be installed in the…
The document outlines a two-sided stepped grid strategy. It sets a grid distance, opens a long after a decline by that distance and a short after a rise by the same distance, then closes a position when price has moved two grid distances upward. Initial…
The article explains a WebSocket subscription workflow for delivering minute-level Chinese A-share market data to a VN.PY strategy. It contrasts a persistent server-push connection with repeated HTTP polling, then outlines connecting to a data source,…
The script describes a mean-reversion strategy that trades a spread between two steel futures contracts. It collects daily closes, standardizes each contract’s recent prices over a rolling window, and subtracts the standardized series to form a spread. A…
This example configures a futures backtest in vn.py with one-minute data, a defined date range, trading costs, contract settings, and an ATR-RSI strategy. It then uses the engine’s optimization setting to search over RSI length and entry parameters,…
The study tests institutional ownership data as a quarterly stock-selection factor in Chinese equities. It measures ownership share, the number of institutions holding a stock, and average holdings per institution as a proxy for ownership concentration. For…
This overview describes a practical Python workflow spanning data collection, database access, and machine-learning, deep-learning, and natural-language-processing tools. Its investing example uses traditional factors measured over rolling 12-month windows…
This configuration specifies a Qlib research workflow for China A-share stocks in the CSI 300 universe. It uses Alpha360 features, robust feature normalization and missing-value filling, and cross-sectional rank normalization for labels. The prediction…
This Chinese equity screening proposal selects stocks with price amplitude above a threshold, a prior-day signal described as major-player control, and a listing age greater than a chosen number of days. Its example implementation also applies filters…
This document describes an Expert Advisor that generates trades from the RVI_Histogram indicator when a bar closes. A selectable trend-detection mode uses either a crossover between the indicator’s main and signal lines together with a cloud-color change, or…
The article argues that even a carefully designed and tested trading system may have a limited useful life. It contrasts the view that a robust system should work across future market conditions with the author’s view that performance should be reviewed…
This document outlines a basic directional system for EUR/USD on a two-hour chart. It opens a long position after a bullish candle whose body exceeds twice the ATR, and opens a short after a bearish candle whose body exceeds the same threshold. A position…
The author recounts using Kelly-style position sizing, mathematical optimization, historical backtests, and a neural network to investigate trading systems. The discussion first explains why a positive win rate alone does not prevent ruin: bet size and…
This intraday DAX strategy applies an opening-range breakout on one-minute data. It records the high and low of the two-hour morning range, then places stop entries above or below those levels after the range ends. The rules restrict entry to before a stated…
This weekly factor report describes two forms of diagnostics for the ten highest-ranked anonymous ModelScore factors: average style exposures estimated through daily multivariate regressions, and average industry-level Rank ICs measuring the cross-sectional…
This post shares a tick-driven script intended to send alerts when a bar crosses above a 200-period moving average after price was below it, with CCI above a threshold. It checks multiple crypto symbols and timeframes, waits for a new bar, then logs a…
This document describes an Expert Advisor that opens trades at a configured time and can close them at another configured time. Users can enable buy orders, sell orders, or both, and set the entry time, entry window duration, trade volume, stop loss, and…
The study applies the CCK approach to detect herding among the constituents of Chinese equity indices. It treats herding as a period when constituent returns move more alike: their co-movement increases while the dispersion of returns falls. The authors also…
The document outlines a daily stock rotation schedule: buy ten stocks at the open, hold each cohort for five days, and sell it at the close on its fifth day. It allocates capital in five equal portions, investing one portion in each day’s new cohort. From…
This document poses a model-design question: whether the number of input factors in a StockRank model relates to the number of leaves per tree or the total number of trees, and whether there are useful rules of thumb for choosing these quantities. It…