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 document presents a framework for testing stock-selection factors. It evaluates each trading day’s stock factor values against returns over subsequent holding periods, aiming to show how predictive information changes as the holding period grows. Daily…
The post asks how to adapt a portfolio-selling routine so that, when the equity allocation exceeds 60% of total portfolio value, the excess exposure is sold from the lowest-ranked holdings. The supplied routine builds a set of currently held securities,…
The post reports an observation from more than six months of intraday modeling in Chinese equities using five-minute bars. At each time point, the author independently tuned parameters with tree-structured Parzen estimation. The reported optimization…
This research summary examines where mutual fund excess returns may come from, separating security-selection skill from timing skill. Timing is framed as adjusting a fund's market beta, with stronger exposure during rising markets and reduced exposure during…
The document introduces quantitative investing as an approach that uses numerical models to build an investment process, contrasting it with methods that rely more on qualitative judgment. It describes how quantitative methods can combine computing with…
This short assignment response defines quantitative investing as turning recurring patterns observed through statistical analysis of financial markets into structured methods for future trading. It mentions stocks, futures, and digital assets, and describes…
The note explains how a Chinese stock daily bar series relates to adjusted and unadjusted prices. It identifies the cited index daily data as back-adjusted and shows that dividing the close by its adjustment factor can recover an unadjusted price. The…
This guide explains how to carry training data for a StockRanker model from BigQuant’s 1.0 environment into version 3.0. In the older environment, it exports the training dataset with date, instrument, label, and the selected feature columns. The file is…
This weekly market report organizes several indicators of Chinese equity liquidity by sector: ETF subscriptions and redemptions, northbound investor flows, estimated allocations from pending and newly raised equity funds, company buybacks, and…
The document examines how trend following could address the equity risk concentration in conventional target-date funds. Their glide paths reduce stock allocations as retirement approaches, yet the portfolio may remain dominated by equity risk, leaving…
This BigQuant support exchange explains a possible source of confusion in backtests: the platform’s `hold_days` setting defines a build-up period during which the strategy can buy, and does not itself require each purchased stock to remain in the portfolio…
The document explains a two-stage model that uses gradient-boosted decision trees to create features for logistic regression. The trees split and combine the original inputs; each sample is then represented by a binary vector marking the leaf it reaches in…
This tutorial demonstrates extracting minute-level stock data for a selected date range with a distributed query platform, then calculating features through SQL-style operators. The examples cover a five-period moving average of closing prices, a…
The document presents an individual-investor approach inspired by Peter Lynch: use familiar products and services to generate company ideas, then assess business quality, growth, debt, and valuation. Its suggested checks include sustained profit growth,…
This research summary examines why stocks can earn excess returns before earnings announcements. It proposes that investors and analysts resolve some uncertainty ahead of the report, supporting price gains before the announcement itself. The study measures…
The document reports a single-factor study of operating-efficiency and growth measures. For six operating factors, it says the analysis used grouped portfolio net values, long-short group returns, information coefficients, and Fama–MacBeth methods. Four…
This research overview presents a workflow for building stock-selection signals from daily price and volume data. Genetic programming generates candidate factors, using rank information coefficients to target linear relationships or mutual information to…
The study summary examines whether active stock selection that increases a mutual fund portfolio’s technological similarity predicts subsequent performance. Company patent distributions are compared using cosine similarity, and a fund’s active technological…
This Chinese-language forum post raises practical questions about what factor weights from a labeling or training process represent. It distinguishes possible interpretations, including neural-network parameters, regression coefficients, and tree-based…
This summary of an equity research report explains portfolio optimization as a framework for managing risk exposures, holdings, weights, turnover, and market impact while incorporating investor views. It argues that simple portfolio construction may perform…
This brief report summarizes a quantitative market-timing view of Chinese A-shares as of early April 2020. It describes the market as being in a bottoming phase with limited downside, and lists sector strength, index and industry valuations, stock-market…
The document presents Wyckoff analysis as a way to interpret market supply and demand through price and volume. It describes three guiding principles: compare demand with supply, treat trading ranges as potential causes of later moves, and assess whether…
The article argues that quantitative trading depends on market understanding as well as technical implementation. It contrasts trend-following and mean-reversion approaches as examples of strategies grounded in different views of market behavior, and…
The article describes a supervised learning approach that classifies whether a stock’s closing price will be higher or lower after a chosen horizon. It smooths historical prices with exponential weighting, then uses six technical indicators—including RSI,…