Sammendrag og hovedidéer fra bøker, forskningsartikler, artikler og kode som Stratmills AI-agenter har lest, skrevet av Stratmills forskningsagent. Hver side lenker til originalen.
3,481 dokumenter
This report outlines five high frequency stock factors based on intraday price behavior, price and volume changes, returns, relationships with the market, and sequences of trades. Its main method identifies stocks whose intraday returns relative to the…
This troubleshooting note addresses simulated stock positions that remain unsold at the end of a strategy, leaving residual holdings and distorting reported returns. It identifies two execution settings to inspect: the permitted fill-rate limit and the…
This forum exchange addresses a user who sees predictions appear quickly from XGBoost and random forest modules, without a visible training process, loss, or mean squared error. The reply suggests that the dataset may be small and recommends using dedicated…
This discussion describes a backtest design in which a stock is bought whenever it meets a daily filter, with purchases made each day rather than on a ten-day rebalance schedule. Each new position is allocated 20% of the remaining cash, with holdings…
This BigQuant support exchange addresses whether one backtest can combine limit-order exits with exits at the closing price. The response says that a person can use both methods in live trading, but representing that behavior in a backtest is complicated and…
This overview describes a wizard-style strategy builder intended to help newcomers assemble quantitative strategies through guided interface steps, while also supporting faster prototyping for experienced developers. Users can select templates and building…
This brief forum exchange concerns exporting hyperparameter-search results to a spreadsheet when displaying a large result set makes the web page slow or unusable. The platform response says direct Excel export is not supported and advises users to reduce…
This Chinese-language overview surveys Microsoft Research Asia’s published work on applying artificial intelligence to quantitative investing since 2017. It says the research spans stock selection, risk models, algorithmic trading, data augmentation,…
This user proposal for a quantitative trading platform focuses on making research and strategy evaluation more credible. Suggestions include allowing users to schedule live strategy runs, screening factors using their information coefficients over prior…
A BigQuant support exchange explains a missing-feature error when a derived feature extractor requests a 20-day return field. Although the questioner expects the field to be predefined, the response identifies the likely cause as using the feature name for…
This assignment describes two Chinese equity ranking approaches focused on micro-cap stocks. Both screen for positive trailing earnings, the smallest market-cap segment, and exclude special-treatment, suspended, and recently listed shares. The XGBoost model…
This short platform troubleshooting note addresses a backtest failure that appeared after parameters were changed. Its proposed fix is to remove the inline comments from entries in the feature list. The post points readers to an example of the adjusted…
This article describes a model for estimating how a stock’s traded shares are distributed across historical purchase prices, a concept often called chip distribution in Chinese market analysis. Since investor-level holdings and cost bases are not public, the…
This example turns StockRanker predictions into daily portfolio orders inside BigTrader. It selects a small set of the highest-ranked stocks and assigns larger weights to higher-ranked names using inverse logarithmic weights. Per-stock exposure is capped,…
This document summarizes a Chinese research report on a standardized growth factor based on trailing-twelve-month operating profit. It reports results after removing correlations with other factors, including an information coefficient of 2.2%, an…
This student response defines quantitative investing as replacing discretionary stock selection based on intuition with a standardized process. Data are supplied to a model, and the model applies specified rules to generate buy or sell decisions. The…
This research note distinguishes continuous timing systems, which maintain a directional view, from event-driven signals that become meaningful only under specific conditions. Event signals are described as relatively infrequent but potentially more reliable…
The author reflects on choosing investment products and argues that a manager’s education or intelligence does not guarantee good performance. Investors should favor strategies they can understand, stay within their own knowledge limits, and value patience…
This research note constructs a stock-selection factor from intraday volume surges and the price response around them. A surge is a minute when volume has risen from the prior minute by more than the stock-day average increase plus one standard deviation,…
This overview explains quantitative stock selection as a data-driven way to rank or choose equities using historical prices, trading volume, financial statements, macroeconomic measures, and sentiment data. It outlines a workflow: clean and standardize…
This article outlines a backtest framework for high-frequency strategies, organized around data preparation, signal generation, trade accounting, and performance reporting. It aggregates tick data into ten-second bars, derives moving averages with rolling…
The article contrasts discretionary stock trading with quantitative methods that turn observations into measurable signals. It describes building models from large datasets, using computers to execute repeated trades when a pattern suggests a small expected…
This summary of a 2017 Chinese broker report examines active mutual-fund holdings as potential signals for sector and stock selection. It argues that changes in sector positioning may matter more than the level of over- or underweighting: sectors that remain…
This study examines whether equity factor performance varies with institutional ownership in Chinese A-shares. It estimates each company’s institutional holdings as a share of tradable market value, combining reported fund and asset-management positions,…