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
The document presents a market-timing experiment that applies a Gaussian hidden Markov model to daily CSI 300 data. Its feature set combines the one-day log return, five-day log return, and log high-low range. The model is configured with six latent states…
The document describes turning intraday order-book and trade data into monthly equity-selection factors. It introduces volume order imbalance (VOI), order imbalance ratio (OIR), and market price bias (MPB). MPB classifies trades by whether buyers or sellers…
This introductory note defines quantitative investing as using numerical methods, models, and algorithms to make investment decisions, including automated execution. It lists potential advantages: rules can reduce emotion-driven choices, computers can…
The document demonstrates a simple cross-sectional factor evaluation for Chinese stocks. It queries daily records for 20-day average turnover and a five-day forward close-to-close return, then groups observations by date and calculates the Spearman rank…
The document proposes an equity factor combining turnover with changes in shareholder counts. It first scales shareholder change by the total shareholder count, aiming to reduce the influence of differences in company size. It then applies a signed…
This review examines target-risk funds, which aim to maintain a relatively stable portfolio risk level through fixed style categories such as aggressive, moderate, and conservative. It describes their role in US retirement accounts, their fund-of-funds fee…
This platform troubleshooting note explains that a shared code sample may run without producing backtest data because it is incomplete. The reported sample lacks a data source and a backtest module, and contains only some backtest component methods. It also…
The report introduces unsupervised learning, focusing on dimensionality reduction and clustering for financial analysis. It describes factor analysis and principal component analysis as ways to compress many stock or bond characteristics into a smaller set…
This Chinese-language research digest introduces two overseas studies in quantitative stock selection and timing. The first examines factor timing empirically, asking whether investors can adjust factor exposure over time, and discusses the challenges and…
This document summarizes a machine learning timing strategy that uses a long short-term memory network to model stock market time series. It presents the model as a way to learn dependencies across observations and adapt to sharp changes in a trend. The…
This research summary outlines a progression from single-factor IC and IR analysis toward attribution in machine-learning models and causal analysis. It says IC and IR are foundational for traditional multifactor research but do not capture interactions…
The document describes monthly stock-selection factors built from news sentiment. Summing a stock’s monthly article sentiment scores combines the direction of coverage with its volume, while averaging scores captures sentiment without the same direct…
This report examines how corporate tax figures relate to business performance and how tax accounting differs from tax cash flows. It distinguishes tax payable, income tax expense, taxes and surcharges, deferred tax assets or liabilities, and cash taxes paid.…
This report applies dynamic drawdown control to an enhanced equity strategy based on GARP, combining valuation and growth ideas. It describes using relative price strength (RPS) to adapt the drawdown-control signal to the market’s relative strength, with the…
This report outlines a strategic and tactical framework for multi-asset allocation. Strategic allocation favors assets with relative strength over a medium-term horizon, while tactical timing adjusts asset weights according to changing conditions. The…
The document explains Elliott Wave theory as a framework for interpreting market trends through a repeating five-wave impulse followed by a three-wave correction. It describes nested wave degrees, three structural rules for impulse waves, and common forms…
This forum post describes a daily stock rotation setup: invest the available cash in one stock, sell it the next day, and repeat. The author reports that orders filled close to fully invested earlier in the backtest but did not use all available capital near…
The article explains how orders travel from a broker through trading infrastructure into an exchange order book, where matching determines whether and at what price they execute. It describes price priority and time priority, then presents a price-selection…
The document links prospect theory and mental accounting to the disposition effect: investors may treat gains and losses differently, which can slow how prices incorporate new information. It proposes that post announcement price drift lasts longer when the…
The document summarizes research on whether hedge funds that perform well continue to do so, depending on overall market conditions. It describes two performance measures based on returns across hedge fund industries: RET_DOWN for weaker markets and RET_UP…
This Chinese-language forum post asks how BigQuant applies transaction costs to convertible bond strategies. It shows a per-order commission configuration with equal buy and sell rates and a minimum charge, then reports that a sell order still appears to…
This Chinese-language Q&A covers practical questions about equity factors, model templates, backtest assessment, and trading tools. It names market capitalization, turnover, momentum, quality, valuation, growth, and profitability as commonly used factors,…
The document describes an A-share stock screen combining three conditions: a 14-period RSI below 65, free-float market capitalization between 5 and 10 billion yuan, and a MACD value from two sessions earlier below zero. It presents RSI and MACD as technical…
This Chinese research summary explores using data-mining models to time factor exposure and rotate among equity factors. It describes random forests conditioned on external market variables to assess when factors may be effective, alongside approaches that…