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 article explains a four-part decomposition of market beta based on whether market and individual stock returns are positive or negative together. The components distinguish joint losses, joint gains, and the two mixed-sign cases. Using realized…
This summary of a 2018 brokerage study examines whether capital-flow measures can help anticipate shifts among equity investment styles. It argues that raw fund-flow observations may add little beyond price and volume because those variables move together,…
This article warns retail equity traders that fast algorithms may exploit order-flow speed differences, bursts of retail enthusiasm, and clustered stop levels. It illustrates possible behaviors: entering ahead of slower orders, buying into a sentiment-driven…
This study examines whether futures-curve shape can rank commodity markets. It explains backwardation, where deferred contracts are cheaper than nearer ones, and contango, where they are more expensive. The article connects these patterns to supply, demand,…
This brief overview proposes a two-stage automated equity approach. Machine learning would rank or filter stocks for potential, while reinforcement learning would determine when to buy or sell the selected names. The intended result is a system that connects…
This platform support thread discusses how to preserve a model after rolling training and whether the final saved artifact represents the intended result. The replies characterize rolling training as a research-stage feature rather than a direct route to…
The post contains a proposed monthly China A-share industry-rotation backtest. It ranks second-level industries by where current price-to-earnings ratios sit within their own rolling 60-session ranges, then selects six industries with the lowest relative…
The article describes turning rolling OHLC windows into sparse, binary candlestick images for a convolutional neural network. Each sample uses 32 time steps, normalized and mapped onto a 128-by-128 grid; three columns represent each candle’s open, high-low…
The article presents a speculative outlook for China’s A-share market in 2026. It anticipates a gradual upward market with a spring positioning period, a stronger phase from May through September, and a sharp interim pullback that it interprets as a possible…
This research digest summarizes two distinct topics. For multi-factor index construction, it contrasts a top-down approach, which combines single-factor indexes using assigned proportions, with a bottom-up approach, which optimizes holdings to increase…
This forum post describes an exploratory factor-construction exercise in the Chinese A-share market. The author says a small modification to a factor combination produced strong short-side results, then describes a revised version that removed the short…
The document outlines three ways to explain portfolio results: style analysis using return regressions, benchmark-relative return decomposition, and multi-factor attribution. It describes the data each approach needs, including portfolio and benchmark…
This opinion article argues that quantitative trading has different effects across market structures. It contrasts a US market it characterizes as institutionally dominated with China’s A-share market, which it portrays as retail-heavy and more driven by…
This review summarizes research on whether skilled active U.S. equity fund managers add more value when prices are noisier. It measures skill mainly through portfolio selectivity, proxied by one minus a fund’s return-model R-squared, and also uses a…
This report summary describes revisions to AlphaNet, a neural network that learns stock-selection factors directly from raw price and volume data. AlphaNet v2 adds six ratio features, replaces pooling and dense layers with an LSTM to capture temporal…
The document summarizes a study of four MSCI smart beta equity indexes—value weighted, equal weighted, momentum, and minimum volatility—against a market-cap-weighted benchmark. Using monthly returns over 1999–2014, the study applies principal component…
The document explains a cost-concentration measure for the estimated purchase costs of a selected share of investors’ holdings. It defines the measure as the difference between the upper and lower bounds of that cost interval divided by their sum. A narrower…
This article outlines an event-driven strategy for Chinese equities, using quarterly reports as the trigger. It treats a published year-over-year increase of more than 30% in attributable net income as a positive event, buys qualifying stocks when reported,…
This essay focuses on how fear can affect trading decisions, including hesitation after losses, reluctance to buy near highs, and difficulty acting during market weakness. Its central idea is that traders need not eliminate fear to act consistently; they can…
The report reviews the development of Smart Beta index funds in China and compares single-factor strategies in A-shares with counterparts in the US. It describes a Chinese market where offerings are relatively early-stage, commonly single-factor, and held…
This report summary describes a Chinese equity ETF rotation approach built from industry indices with matching exchange-traded funds. It selects 14 industries from the broader industry classification and rotates exposure among their ETFs. The strategy is…
This strategy ranks stocks across mainland China’s A-share market using a small-cap factor and a five-period momentum measure. It combines the market-cap rank with momentum into a composite score, selects the top 50 names, and assigns equal weights. The…
The article argues that quantitative trading is an execution method, not a source of returns by itself. A trading system can automate orders and support consistent discipline, but it cannot make a weak or faulty strategy profitable. It also questions the…
The document reviews tactical and dynamic asset allocation, then focuses on predicting short-term movements in Chinese equity indices. It compares logistic regression, artificial neural networks, and support vector machines across different inputs and…