Kokkuvõtted ja põhiideed raamatutest, teadustöödest, artiklitest ja koodist, mida meie AI-agendid loevad. Need on koostanud Stratmilli uurimisagent. Igal lehel on link originaalile.
3,481 dokumenti
This tutorial shows how to calculate and inspect one factor feature in BigQuant without running a full strategy workflow. Its example factor counts, over a rolling window, the days when a 10-day average-turnover measure exceeds a threshold. The steps are to…
This introductory guide explains machine learning through a house-price prediction example. It distinguishes supervised learning, which learns from examples with known outcomes, from unsupervised learning, which searches unlabeled data for groupings or…
This article argues that asset prices and expected returns can be understood by modeling who demands assets, rather than focusing only on how company characteristics predict returns. With supply often relatively stable, changes in investor demand can move…
This essay examines why a discretionary trader’s apparently simple rules may produce poor automated decisions. It argues that verbal rules often omit implicit conditions, such as market sentiment, macro context, and sector rotation, that influence a trader’s…
This note explains how to exclude specially treated (“ST”) Chinese stocks from both the training and validation data flows in a visual AI stock-selection strategy. In the older workflow, it inserts a shared filtering module before missing-data handling in…
This Chinese-language assignment turns a discretionary technical-analysis approach into a rule-based stock selection outline. It first filters the eligible stock pool by excluding specified exchange listings and special-treatment stocks, as well as firms…
The article summarizes research on a mismatch between active equity funds’ management capacity and the assets they attract. It argues that investors often mistake returns associated with common factor exposures for evidence of manager skill. Funds with…
The document presents several model-generated views on investing, quantitative trading, and platforms such as BigQuant. Its investing discussion emphasizes asset value, the time value of money, risk and return, opportunity cost, diversification, and…
This post describes a low-volatility dividend strategy built around a static dividend-yield measure. The author says the strategy was developed after finding a problem in a rolling 12-month dividend-yield factor: when two distributions occurred less than a…
This document summarizes an analysis of China Europe Fund manager Zhou Yingbo and the fund China Europe Times Pioneer A. It reports the fund’s historical returns and drawdown in relation to its benchmark and peer group, and cites a Treynor-Mazuy model…
The report presents a way to speed up portfolio optimization while retaining a covariance estimate built with statistical shrinkage. It starts with a linearly shrunk covariance matrix, decomposes it spectrally, keeps the components associated with the…
A user reports unusually strong factor-analysis returns after combining StockRank with a gradient factor built from a two-day moving average. They suspect look-ahead bias because the strategy produces no trade data in a simulated account, while an XGBoost…
This article describes a set of purported Chinese A-share rules intended to curb speed and access advantages in quantitative trading. It says the measures would add network delay, end broker-dedicated trading positions, cap order submissions, require…
This report compares methods for forecasting asset return covariance, a key input to minimum-variance and risk-budget portfolios. It evaluates historical and shrinkage covariance estimates, exponentially weighted moving averages, and multivariate GARCH…
This brief introduces two research papers on asset allocation and mutual fund performance prediction. The first examines statistical problems in forecasting long-term returns, including estimation errors and misinterpretation of model parameters. It reports…
The discussion addresses a platform issue where a strategy can complete a one-day backtest but fails in simulated trading because its training data is empty. The proposed diagnosis focuses on how the M3 module extracts data and whether its date range is…
This research summary examines stock and industry characteristics associated with long term performance across Chinese A-share bull and bear markets. It argues that revenue growth is especially relevant in rising markets, while profitability and valuation…
This review summarizes research on whether factor momentum explains industry momentum. The underlying study ranks factor portfolios by their recent returns, takes long positions in recent winners and short positions in losers, and compares the resulting…
This report studies twelve revenue, profit, operating cash flow, and return-on-equity growth measures in Chinese A-shares. It compares their industry and size relationships, then evaluates them using industry-neutral portfolio sorts, cross-sectional return…
The document describes a qualitative and quantitative approach to sector rotation based on economic cycles. It treats commodity prices, represented by the CRB spot index, as a timely gauge of the real economy, and links long, medium, and short cycles with…
This report examines open-interest information in Chinese equity index futures from two perspectives. At the intraday level, it applies statistical methods to minute data to identify samples associated with aggressive trading and analyze trading behavior. At…
This report surveys quantitative enhancement of Chinese equity indices, aiming to outperform a benchmark while controlling tracking error. It places multi-factor models at the center of the approach: estimate returns and risks through factor exposures, then…
This discussion concerns industry neutralization of a stock factor, using industry indicators as explanatory variables in an ordinary least squares regression. The example joins daily stock data with industry classifications, creates dummy variables,…
The document describes a proposed stock-trading system that combines moving-average analysis, an LSTM price-forecasting model, and investor risk assessments to generate personalized buy and sell signals. It says the researchers used 20 years of daily data…