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.
5,018 documents
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 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…
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 example describes an equity opening-range breakout system split between two agents. A research agent scans a configured universe and ranks breakouts using completed regular-session bars beginning at the market open. A separate trading and risk agent…
This essay contrasts three broad approaches to investing through Warren Buffett, George Soros, and James Simons. It describes Soros’s reflexivity framework, in which investor beliefs can move prices and price changes can then reinforce those beliefs. Buffett…
This study summary examines whether index futures information can improve high-frequency technical trading rules for Chinese index ETFs. It uses genetic programming to evolve rules from five-minute price data for CSI 300 and CSI 500 ETFs and their…
This benchmark page compares stock-ranking and return-prediction models in Qlib workflows using the Alpha158 and Alpha360 datasets. It evaluates signals with information and rank correlations, and evaluates portfolios with annualized return, information…
This report describes combining individual-stock timing with multi-factor stock selection in a T+0 strategy. It uses deep-learning ideas to reduce a multidimensional space of parameter settings and win rates, then examines how performance changes across…
This report compares machine-learning stock-selection models trained with conventional return labels against models using information ratio or Calmar ratio labels. The alternative labels incorporate aspects of the path within the evaluation period, including…
This explanation describes a factor evaluation score derived from rolling Elastic Net regressions that include all submitted factors together. The model predicts each stock’s next-day return after cross-sectional standardization, fits on rolling windows, and…
This systematic literature review summarizes research on artificial intelligence in financial trading published from 2015 to 2023. It reports screening 143 papers across multiple research databases and compares the markets and assets studied, analytical…
This paper summary describes an online learning method based on adversarial experts for selecting parameters in a zero-cost portfolio of technical trading strategies. The method combines a collection of historically tested strategies and studies their…
The document summarizes research on an adversarial-experts online learning algorithm that adjusts parameters for a zero-cost portfolio of technical trading strategies. The approach combines a collection of strategies into an aggregate portfolio and studies…
The note describes two ways to address an ErrorReturnCode_84 encountered when running a BigQuant strategy with a StockRanker module. One option is to increase the AI Studio compute configuration. The other is to reduce the dataset and lower the model’s…
This configuration specifies a Qlib workflow that trains a PyTorch deep neural network on Alpha158 features for the CSI 500 universe. The data spans 2008 through mid-2020, with training through 2014, validation during 2015–2016, and testing from 2017 onward.…
This tutorial introduces TensorFlow concepts, including tensors, computation graphs, automatic differentiation, and optimizers, then outlines a financial time-series example using a long short-term memory network. The workflow collects historical stock…
This Chinese strategy note describes turning discretionary stock-screening rules into Boolean model features for a CNN classifier. The proposed universe favors companies with positive profitability and valuation measures, short-term strength, positive…
This example organizes an AI-assisted sector ETF strategy into research pods for technology, financials, healthcare, energy, and consumer sectors. The pods rank ETFs using recent news and macroeconomic context, with optional company or sector filings where…
This indicator identifies bullish and bearish order blocks after market structure breaks, then attaches a probability derived from a supervised classifier trained on recent chart data. Its inputs are RSI, money-flow index, relative ATR, and a volume z-score;…
This configuration specifies a Qlib experiment that trains an ALSTM model on China’s CSI 300 universe and evaluates stock selections in a portfolio backtest. The data handler uses Alpha360 features, robust feature normalization, missing-value filling, and…
This Chinese-language report summary surveys how artificial intelligence may be applied across asset management. It describes hedge funds and investment banks adopting AI, then discusses potential uses in investment research, trading, risk management,…
The article presents four ways to inspect a random forest: permutation-based feature importance, variation among individual tree predictions, per-observation prediction paths, and partial dependence plots (PDPs). For permutation importance, it compares a…
This study explores genetic programming as a way to discover formula-based signals for commodity futures trading. It adapts a genetic programming package to search combinations of market data and operators, aiming to find signals that could complement…
The document shows a stock-ranking workflow that derives 30-day and 90-day returns, ranks securities cross-sectionally, filters the universe, and creates a forward-return label for model training. A StockRanker module trains on historical data and predicts…