Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
3,481 documents
This short discussion explains a label distribution chart used when building an AI trading strategy. The horizontal axis represents label identifiers, and the vertical axis shows how many observations belong to each label. The chart can reveal labels with…
This report presents a three-layer fundamental quant framework: macro indicators and scenario analysis, sector-level earnings and valuation measures, and portfolio strategies. Its macro view combines growth, monetary and credit conditions, and inventory…
This report excerpt reviews several Chinese equity strategies for the week ending around July 19, 2020. It says valuation and quality factors performed relatively well while momentum weakened. The CSI 300 and CSI 500 enhanced portfolios both declined for the…
The document describes a framework for deciding whether a candidate multifactor strategy adds value alongside a portfolio of smart beta exposures. It models each advanced beta as a combination of exposures to a small set of investable “elementary” factors,…
This study examines how stock volatility relates to reversal and other factor returns in China’s A-share market, controlling for market capitalization and industry effects. It reports that stocks with weaker past returns tended to outperform later across…
The article reviews research linking firms’ incentives to manage investor expectations with earnings announcement premiums and seasonal stock returns. It builds an ex ante expectation management incentive score from analyst coverage and institutional…
This study builds a convertible-bond strategy that separates bonds into equity-like, balanced, and bond-like groups using parity premium relative to bond value. It models each bond as a floor component plus option time value, then examines where factor…
This opinion article argues that individual A-share traders face disadvantages against quantitative firms through both speed and market rules. It contrasts claimed latency figures for colocated trading systems and retail apps, then describes the T+1…
This research summary reports tests of 23 alpha factors across seven categories in the Hang Seng Composite and Stock Connect universes. It says valuation, profitability, and growth factors were significant, with information coefficients around 3%. A…
This training overview outlines a proposed workflow for using multimodal large language models in quantitative investing. It combines time-series databases, knowledge graphs, and reinforcement learning in a pipeline that connects data, signals, and portfolio…
The report describes a framework that combines strategic asset allocation with tactical timing. Strategic weights favor assets that are relatively strong under different economic conditions, while tactical adjustments change overweights and underweights. Its…
This report analyzes the performance and portfolio of a Chinese mixed equity fund managed by Lin Yingrui. It describes the manager’s approach as selecting leading companies in sectors linked to China’s economic transition while adjusting broad asset…
This opinion piece argues that quantitative trading’s advantages extend beyond execution speed. It emphasizes systematic research and iteration: models can combine many fundamental and price-based signals, test relationships across historical data, and…
This overview compares machine learning and deep learning methods for predicting stock prices and trends. It describes LSTM and GRU recurrent networks for sequential data, CNNs for extracting patterns, bidirectional LSTMs, and deep neural networks. It also…
This intraday A-share strategy combines strong thematic sectors with stocks that have recently reached their daily price limits. It ranks concept indexes by short- and medium-term returns, retaining the top two percent on both measures, then screens stocks…
This literature review explains time-series and cross-sectional momentum strategies applied to equity anomaly factors. The time-series approach buys factors with positive trailing returns and shorts those with negative returns; the cross-sectional approach…
This research summary examines whether extreme investor sentiment can help identify short-term industry allocation opportunities. It argues that industry valuation comparisons are difficult because sectors differ in profitability and asset intensity,…
This report studies whether one industry’s past returns can help predict another industry’s future returns. It argues that information may spread gradually across related industries because investors cannot immediately assess every impact of a new shock. The…
This study examines macro momentum across stock markets and its use for timing Chinese equities. It differs from price-based trend following by using macroeconomic indicators to generate signals. For a universe of 24 country equity indexes, it considers…
The document summarizes research that builds a German FEARS sentiment index from Google search activity and links it to individual investors’ trades and stock returns. The index is constructed from searches for German terms related to expectations and…
A BigQuant user asks why a strategy continues to submit buy orders even though the platform logs cancel them for insufficient cash. The example allocates a daily portion of portfolio value, reads the reported cash balance, calculates an order value, and…
This brief BigQuant assignment proposes a contrarian stock strategy based on the idea that unusually low trading activity may accompany a price low. It buys the five stocks with the lowest turnover and holds them for five days, seeking a reversal. The…
This article describes a discretionary intraday approach to trading an existing stock position in an effort to lower its effective cost. It distinguishes buying before selling in an uptrend from selling before buying in a downtrend, and frames entries around…
This forum post describes a feature calculated from the 000300.HIX index data. It derives daily returns from the close, calculates a rolling standard deviation over 250 observations, and divides that volatility measure by average turnover over the same…