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 introduces graph representations for modeling relationships among financial assets, arguing that stocks cannot be understood solely as independent observations. Graphs can encode different kinds of links, including sector membership, return…
This post proposes screening stocks in the beverage and alcohol import-export industry using an RSI below 65 and a Morning Star candlestick pattern. The RSI is calculated over 14 periods, while the candlestick signal is identified from open, high, low, and…
This research overview describes two broad approaches to absolute-return investing: combining equities and bonds, and hedging or taking exposures through derivatives. It lists stock-bond rebalancing, target-volatility, risk-parity, and risk-budgeting…
This report studies cases where Chinese listed companies’ annual earnings forecasts later change, either through a revision announcement or a discrepancy in the formal results. It uses a multinomial Logit model to assess whether company financial data,…
This overview presents QLib as an open-source quantitative research platform that supports data preparation, model training, portfolio construction, risk analysis, backtesting, and execution research. It notes support for supervised learning, market-dynamics…
This brief strategy note proposes ranking or selecting stocks by the deviation in price impact associated with five-minute capital flows. Its stated hypothesis is that stocks with smaller price-impact deviations perform better later; it describes these as…
The document summarizes the ResNet paper’s approach to training deep convolutional neural networks. Instead of having stacked layers learn a full transformation directly, residual learning lets them learn a change relative to their input. The paper’s…
This July 2018 research summary reviews U.S. equities, gold, and crude oil using earnings, interest rates, investor risk appetite, currency moves, supply conditions, and inventories. For U.S. stocks, it argues that earnings expectations remain supportive and…
This BigQuant forum post presents a SQL query intended to calculate sector-level and market-level returns, compound each series across a rolling window, and derive an information-ratio-like value. The author reports that the underlying daily inputs appear…
The document summarizes research on whether seasonal shifts in investor mood help explain recurring cross-sectional patterns in stock returns. It treats January, March, and Fridays as relatively optimistic periods, and September, October, and Mondays as…
This reference surveys common technical indicators and explains several price, risk, valuation, and execution measures with formulas and numerical illustrations. Topics include simple and exponential moving averages, RSI, beta, Sharpe ratio, price momentum,…
This article presents a discretionary approach to rotating from an established leading stock or theme into a newer one. It watches for signs of a theme gaining breadth, such as multiple limit-up stocks, rising sector performance, and an increasing count of…
This research summary examines newly launched and large mutual funds in China during the first half of 2020, focusing on their managers’ possible portfolio choices as funds completed or continued building positions. It argues that manager-level analysis can…
This meetup Q&A covers practical choices in quantitative strategy design. It says researchers can choose the forward-return horizon used as the target when calculating information coefficients, and points to model-based and scoring templates. For…
This document introduces generative adversarial networks (GANs) as a machine learning framework with two neural networks: a generator that creates samples and a discriminator that judges them. Their competing objectives form an adversarial training process.…
This report summary describes revisions to AlphaNet, a neural network that learns stock-selection factors from price and volume data. AlphaNet-v2 adds six ratio features, replaces pooling and fully connected layers with an LSTM to capture temporal patterns,…
This May 2020 market note reviews the reported Sell-in-May calendar pattern in Chinese A-shares and states that defense and military stocks historically performed best from May through September. Given the possibility of a May pullback, its positioning view…
The transcript surveys four ways quantitative methods enter trading: high frequency strategies, statistical arbitrage, execution algorithms, and quantitative tools used alongside discretionary investing. It describes market making as earning bid–ask spreads,…
This research summary addresses how to combine highly correlated stock-selection factors when there are too many inputs to orthogonalize efficiently or when orthogonalization fails to retain their shared information. It describes reducing each factor group…
The report describes applying Thompson Sampling, an online learning method, to adjust a multi-factor investment model as market leadership changes. It uses China A-share constituents from the CSI 300 and CSI 500, with valuation, profitability, growth,…
This collection of trading anecdotes describes manual, high-frequency intraday futures scalping based on order-book changes, quick reactions, and repeated attempts to capture small price differences. Practitioners emphasize watching volume and position…
This article surveys Microsoft Research’s published work on AI for quantitative investing, especially Chinese equity selection. It explains methods that use graph neural networks to represent relationships among stocks, attention mechanisms to adapt to…
This overview presents themes MSCI identified for ESG investing over the coming decade. It groups them into climate and equity, the mainstreaming of ESG, and emerging risks and opportunities. Topics include corporate pressure on net-zero supply chains,…
This weekly report reviews market conditions following a sharp equity selloff and describes trend signals across U.S. and Chinese equities, Hong Kong shares, gold, and bonds. Its trend-following system indicated rising trends in U.S. equities and bonds,…