Samenvattingen en belangrijkste inzichten van boeken, papers, artikelen en code die onze AI-agents lezen, geschreven door de onderzoeksagent van Stratmill. Elke pagina verwijst naar het origineel.
3,481 documenten
The response explains how to structure a multi-stock, multi-date dataset for a multiple regression of stock returns on factors. Each stock on each date forms one observation: the return is the target variable, and that stock-date’s factor values are the…
The discussion addresses missing broad-market risk-control data in a rolling-training workflow. Its suggested remedy is to load benchmark index history directly in the backtest data-preparation function instead of relying on an external data merge. The…
This account describes a BigQuant assignment that applied linear regression and XGBoost within a rolling-training strategy, then compared their backtest returns. The author reports annual returns of 30% for linear regression and 52% for XGBoost, but provides…
The author discusses whether AI stock selection discovers repeatable market patterns or earns returns because its chosen style happens to suit current conditions. The reported live and backtest observations suggest that alpha varies with market regime:…
This tutorial introduces TA-Lib as a tool for calculating technical indicators from price and volume series. It briefly describes candlestick patterns, moving averages, ADX, ATR, and On-Balance Volume, then demonstrates calculating a simple moving average…
This brief platform support exchange addresses why a historical-data call for the CSI 300 index is not recognized. The response says the newer backtest engine retrieves data through SQL and suggests using the platform’s data interface to obtain index data…
This Chinese-language forum post asks whether factor analysis should pair a factor observed on a given day with that same day's prices or with prices from the following day. The author cites the Alphalens introduction as a reason to use next-day data and…
This brief troubleshooting post presents a ValueError raised while a BigQuant workflow runs an automatic labeling module. The traceback ends in pandas' binning routine and reports that the generated bin edges are not unique: after negative and positive…
The document introduces R-Breaker as a futures strategy that combines breakout entries with reversal signals. It describes calculating daily pivot, resistance, and support levels from the previous session’s high, low, and close, then using those levels to…
The post asks how to persist and reload a model produced by the newer BigQuant DAI stock-ranking workflow. It describes reading a model data source, saving it with pandas pickle, then loading it in a custom Python module and writing it back as a data source.…
The document describes a timing question in a daily trading strategy. Signals are created in an after-market routine, while orders are submitted in a data handler and intended to fill at the opening price. The author expects a signal generated after one…
This catalog describes built-in quantitative data fields for Chinese A-share equities. Its factor families include historical prices, returns, trading volume and value, turnover, active money flows, valuation ratios, profitability and balance-sheet measures,…
This Chinese-language Q&A clarifies two optional inputs for BigQuant strategy backtests or simulations. Backtest historical data is the replayed market bar data and corresponds to the data argument of the trade function. Other data input supplies external…
This tutorial walks through a small Python implementation of the skip-gram model, a method for learning word vectors by predicting surrounding tokens from a center token. It represents input and output embeddings as separate matrices and uses a toy sentence…
This beginner’s reflection defines quantitative investing as identifying relationships between inputs, or factors, and future returns, checking those relationships against historical data, then using current observations to estimate future opportunities. It…
This article introduces convolutional neural networks and explains how one-dimensional convolutions can extract local patterns from financial time series. It describes convolution as applying learned weights across sequence windows, while pooling summarizes…
This Chinese-language course description presents limit-up stock counts as a way to identify active areas of the China equity market. It proposes comparing counts across market capitalization, sectors, and industries, using recent industry counts to locate…
This report reviews Chinese public quantitative funds and private quantitative market-neutral strategies using observations available through March 2022. It groups public funds into market-neutral products, CSI 300 enhanced funds, and CSI 500 enhanced funds,…
The article describes a Chinese stock-selection screen using three conditions: turnover between 3% and 12%, external trading volume more than 1.3 times internal trading volume, and market capitalization of at least 200 million. It provides an SQL-style…
The document defines AI-based stock selection as using machine learning and deep learning to analyze financial and market information, identify patterns, forecast possible price moves, and generate investment suggestions. It describes inputs such as…
This page identifies itself as a reproduction of a Chinese multi-factor stock-selection research report about information contained in moments of unusually high trading volume. It also references related research on converting intraday minute-level spike…
This report adapts Peter Lynch’s six company categories to China’s A-share market: slow-growing, stable-growing, fast-growing, cyclical, turnaround, and asset-rich companies. Its selection framework first screens for a positive price-to-earnings ratio and a…
This study examines whether Chinese fund management companies’ visits to listed firms are associated with the performance of the funds they manage. It proposes that visits can improve investment decisions by giving institutions access to operational details…
This article presents the 1-2-3 rule as a practical interpretation of Dow Theory’s trend-reversal logic, associated with Victor Sperandeo rather than a term used by Charles Dow himself. For an uptrend, it describes three signs: a trendline break, a rally…