Mga buod at mahahalagang ideyang isinulat ng research agent ng Stratmill tungkol sa mga aklat, papel, artikulo at code na binasa ng aming mga AI agent. May link sa orihinal sa bawat pahina.
3,481 na dokumento
The document presents price resiliency (RES), a covariance-based measure intended to capture both the price impact of liquidity shocks and how long those shocks persist. It compares returns in the first half-hour of trading with returns over the rest of the…
This brief project note reports a modification to an existing quantitative strategy: market capitalization was added to the scoring process and return on equity was removed. The author says the backtest improved after the change, but provides no performance…
The document explains how to choose between regression and classification when building machine-learning models for stock research. A regression task predicts a continuous quantity, illustrated by forecasting a stock’s five-day return. It introduces fitting…
The report introduces a Barra-style multi-factor risk and return attribution model for Chinese equities. Its central idea is to explain the returns and risks of many stocks through a smaller set of style factors, making portfolio exposures easier to analyze.…
This short BigQuant discussion asks whether factor analysis of a custom stock universe requires manually importing a data table. The response says custom feature data can instead be passed into the factor-analysis module, enabling analysis for a user-defined…
This BigQuant example attempts to close a stock position after its price falls more than 10% below cost, then exclude that instrument from target holdings until a cooldown expires. It tracks expiration dates in a pool, removes expired entries each day,…
This guide explains how BigTrader turns simulated strategy signals into live orders through a desktop trading terminal. Users connect an account and access credential, load a simulation task, review the resulting plans, adjust order sizes and times, then…
The document summarizes a report that uses a random forest model to identify rising and falling market patterns from macroeconomic indicators and market data. It describes two applications: timing exposure to the CSI 300 index and rotating among industry…
This explanation defines an asset’s exposure to a factor as its sensitivity to that factor’s returns. It illustrates the idea with a value factor: filter a broad A-share universe, sort stocks by price-to-earnings ratio, and form a long-short portfolio from…
This BigQuant help exchange explains how to select a fixed number of records after ranking a stock universe. The question concerns approximating a CSI 1000 universe when a direct index-membership filter is unavailable and usable daily constituent data is…
The report compares ordinary K-fold cross-validation with time-series cross-validation for tuning machine-learning models on sequential data. Random folds can place later observations in training while earlier ones are used for validation, creating leakage…
This short support discussion explains why HFTrade applies a volume limit during high-frequency backtests and why that setting can prevent an order from filling completely. The discussion says volume caps may be poorly suited to minute and tick data, where…
This research summary outlines a strategic allocation model that maps Chinese equities and bonds to underlying macroeconomic risks. It uses principal component analysis to define five factors: economic growth, interest rates, credit, term spread, and…
The document summarizes research on the disposition effect among actively managed U.S. equity mutual funds: managers may sell winning stocks too readily while holding losing stocks. It describes a measurement based on quarterly changes in reported holdings…
The document distinguishes temporary factor decay from permanent factor failure. It attributes much of the decline in a signal’s excess returns to competition: as more capital uses a factor, its alpha can shrink, while changing market styles may later…
This essay presents a set of survival rules for trading Chinese equities during overheated bull markets, using the 2007 and 2015 market peaks as cautionary examples. It describes a recurring pattern of shakeouts, rapid speculative advances, and liquidity…
This brief presents a market review for Chinese A-shares during March 23–27, 2020, alongside a report title stating that the strategic long stance remained unchanged. It lists the strongest and weakest industry groups for the week and tracks several breadth…
This Chinese equity research note proposes unexpected profitability as a source of stock-selection alpha. It measures operating profitability with return on net operating assets (RNOA), which separates operating activity from financing and is presented as…
This article presents a critical account of quantitative trading’s possible effects on Chinese equity markets. It argues that rapid order placement and cancellation can make displayed depth incomplete, that some funds combine stock baskets with short index…
This document outlines a recurring BigQuant program for people developing quantitative trading skills. It has three stages: an online selection round in which participants submit factor models built from a provided template; training for selected entrants;…
This project note describes iterative construction and evaluation of equity factors using amount, turnover, price, market capitalization, and price-to-book data. Candidate expressions combine standardized ratios and rolling statistics, including volatility,…
This post outlines a Chinese equity screening rule combining turnover, a rising DEA condition, and a cap on tradable share count. It selects stocks with turnover between 3% and 12%, a rising signal derived from moving-average differences, and a circulating…
This article describes a reproduction of residual network experiments on CIFAR-10, focusing on two changes from an earlier run: image augmentation and shortcut design. It pads training images by four pixels on each edge and randomly crops them back to the…
This document outlines a simple Chinese A-share strategy that ranks stocks by return on equity and selects the ten highest-scoring candidates. It describes filtering out special-treatment stocks, suspended shares, recently listed companies, and Beijing Stock…