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
The document describes a partial-replication method that selects a small set of stocks to track an index by capturing the systematic factors driving its returns. It estimates the number of factors, uses principal components to estimate factor loadings, then…
This article adapts a machine-learning value strategy to Chinese A-shares. It trains an XGBoost regression model on accounting and company characteristics to forecast future price-to-book ratios. The gap between forecast and current price-to-book, scaled by…
This expert-advisor strategy enters a position when the ColorPEMA_Digit indicator changes color at a bar close. It includes an optional time-based exit: when a trade has been open longer than a preset number of minutes, the position is closed immediately.…
The report introduces generative adversarial networks (GANs) for quantitative finance. A generator creates synthetic market data while a discriminator tries to distinguish it from real data; alternating training aims to make the generated series resemble the…
This article summarizes research on whether mutual fund managers adjust market exposure ahead of rises and declines. It describes Treynor–Mazuy and Henriksson–Merton regression tests, augmented with market, size, value, and momentum factors, and compares…
This expert advisor uses a modified Awesome Oscillator (AO) to generate reversal signals. It buys when a green AO bar appears below zero after a run of red bars, and sells when a red bar appears above zero after a run of green bars. Stochastics and Bollinger…
A BigQuant community post reports that an XGBoost template completes historical backtesting but fails when submitted for simulated trading. The traceback shows the failure occurring while training data is prepared: the code calculates ranking group sizes…
This strategy trades the DAX on five-minute bars, opening positions during a specified morning window. Long entries require TEMA to turn upward while smoothed Directional Indicator values rise from below zero; shorts use the inverse conditions. It limits…
This stock-selection rule combines three conditions: membership in the metaverse theme, a daily high-low range above 1%, and a KDJ reading below 20. The article describes the range condition as seeking more active price movement and treats the low KDJ value…
A VeighNa community exchange addresses a CTA strategy whose indicators appeared unchanged after live initialization, while the strategy still placed orders. The user mentions a Dual Thrust strategy and uncertainty about whether a period running in no-UI mode…
The document presents TS-Boost as a machine-learning framework for equity factor selection, motivated by two challenges in financial data: changing distributions across time and low signal-to-noise ratios. Instead of pooling observations from many dates into…
The discussion explains why a backtest’s cumulative return can appear inconsistent with profit and loss shown in exported position details. The key distinction is that the export described here records stocks still held at the end of each day. It therefore…
This research note explains how one-dimensional convolutional neural networks can extract local patterns from financial time series, and how ResNet skip connections help address performance degradation as networks deepen. Its proposed stock-ranking setup…
The discussion explains two data needs when running simulated trading in VeighNa. For live simulated trading, the platform must connect to a market interface, with a test account and CTP given as examples, so it can receive real-time quotes. For historical…
The strategy applies K-Means clustering to daily index features, such as recent average volatility, MACD, and average trading volume, to group trading days into market regimes. With two clusters, it compares each day’s feature vector with cluster centers,…
The document implements two momentum approaches for a single asset: MACD from short and long exponential moving averages of closing prices, and the Awesome Oscillator from short and long simple moving averages of the high-low midpoint. Both use…
This stock selection rule combines a daily turnover range of 3% to 12%, a newly formed KDJ golden cross, and prior-day auction turnover above 0.26. The article frames the turnover range as a way to select active stocks, the KDJ crossover as a momentum or…
This report summary describes a composite signal for forecasting changes in futures basis using high-frequency ETF premiums and discounts. It separates ETF observations into intraday comparisons, such as the close versus the open or the day's average, and…
This page summarizes two research papers rather than presenting their full methods. The first applies a non-proportional-thinking model to explain how prices relative to reference values may shape reactions to new information. It proposes that stocks priced…
This overview describes alpha as a return opportunity identified by studying historical data and relationships among market, company, macroeconomic, and text information. It outlines a research cycle: develop an economic rationale and measurable signal,…
The post asks whether a backtesting or simulation setup's commission setting includes the stamp tax charged on stock sales in mainland China. The author says that, for frequent portfolio turnover, this tax could materially reduce estimated returns compared…
This announcement outlines a workshop on applying Kronos, a language-model-style system designed for financial price series, to CTA research. Its central idea is to represent candlesticks as tokens so a Transformer can learn patterns across sequences. The…
The Expert Advisor described here searches a chosen number of recent bars on a configurable timeframe for the highest high and lowest low. It then places a Buy Stop above the high and a Sell Stop below the low, with the distance set by an indentation…
This Chinese-language post presents a short-term stock selection screen using three conditions: turnover ratio between 3% and 12%, opening price near the 10-day moving average, and intraday range of at least 1% of the opening price. The opening-price…