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 forum post raises a data-preparation problem in an LSTM trading strategy. The author reports that filtering rows before rolling sequence windows can remove observations that should remain part of the temporal context, causing later observations to shift…
The article compares two ways to build equity strategies: train a predictive model on chosen factors and a defined stock universe, or specify screening conditions directly. The AI approach can be quicker to assemble, but its behavior may be hard to diagnose…
The report reassesses valuation, growth, technical, and risk factors in Chinese A-shares after removing industry and style influences. Its core method is to adjust factor data for exposures such as industry, market capitalization, or beta, then test whether…
Fundamental quantitative investing applies statistical methods and algorithms to company accounts, industry information, and macroeconomic data to rank stocks by estimated value or quality. The document describes analyzing profitability, financial strength,…
The paper examines how five emotions expressed on Sina Weibo—anger, disgust, fear, joy, and sadness—relate to Chinese stock returns. It uses machine learning to classify posts and wavelet analysis to study how the relationship changes over time and across…
This competition entry modifies a Deep Alpha convolutional neural network by supplying five time slices for each of 98 factors, rather than using a single slice. The network structure and most parameters remain close to the original model because training…
This report examines changes in concentrated holdings among Chinese active equity funds using quarterly disclosures and a daily estimate of fund exposure to a core group of crowded stocks. It compares the core group’s holdings over time, separates changes in…
This support exchange concerns an IndexError that occurs when a Chinese convertible bond data table is read during a backtest. The same table can be read outside the backtest, and comparable reads of other tables within the backtest reportedly succeed. That…
This short BigQuant assignment describes a daily stock-ranking approach built from a combination of total equity and trailing-twelve-month average return on equity. Each day, the strategy holds stocks with comparatively high values of the combined factor. It…
This overview summarizes six ICML 2022 papers selected by G-Research staff. The topics include convex formulations for training two-layer ReLU networks, linear-time attention, branch-and-bound optimization of shallow decision trees, structured matrices for…
This overview introduces three types of company data associated with FactSet: a six-level product and service based industry classification, company-to-company supply-chain relationships, and geographic revenue exposure. The classification is presented as a…
This forum exchange explains why a sell order can disappear in an event-driven backtest when the stock is suspended on the scheduled execution day. The order was generated on one day, but the attempted match on the next day failed because trading was halted;…
This weekly report describes two quantitative equity approaches. The first builds on holdings of successful active funds, then applies quantitative selection to create an enhanced portfolio benchmarked against active equity funds rather than broad market…
This note explains beta as a measure of an asset’s market risk exposure and introduces the Fama–French three-factor model as a way to capture size and value style exposures. It describes how to quantify style performance with long-short portfolios: small-cap…
This research proposes a stock selection factor that estimates similarity between companies using ten financial measures spanning profitability, solvency, operating efficiency, and growth. After cross-sectional normalization, it uses cosine similarity to…
This post sketches an experimental model for identifying leading stocks, using gradient boosted regression to score shares within a rolling window. The proposed label gives higher scores to stocks that rise more, experience smaller drawdowns, and break out…
This China equity strategy ranks stocks cross-sectionally using circulating market capitalization and earnings per share, combining the rankings into a total score and sorting from low to high. It excludes special-treatment and suspended stocks, requires…
The article argues that retail traders often sell during fear and re-enter during excitement, while institutions may accumulate during declines and distribute into renewed demand. It recommends treating oneself as a follower, watching capital flows, and…
This review of research on equity factor investing explains why low unconditional correlations between factors may not provide protection when macroeconomic conditions deteriorate. It describes selecting fast-moving state variables that reflect expectations…
This document summarizes a 2021 presentation on tools for classifying industry-themed funds and building quantitative industry allocation strategies. Its proposed framework brings together macroeconomic drivers that may affect sector conditions, comparisons…
This report examines why investment portfolios turn over, how to manage that turnover, and how turnover control affects portfolio outcomes. It frames the drivers across the research and trading process: alpha changes influence target holdings, optimization…
The document describes a hybrid approach that combines ARMA-GARCH models with several neural network types to identify market patterns and predict the direction of shocks in defense equities and foreign exchange. ARMA-GARCH models capture linear time-series…
This note describes a daily liquidity signal built from intraday order book snapshots. It sums bid and ask volumes across the first five levels, then measures their normalized imbalance as the difference divided by the total. Separately, it calculates…
The document briefly introduces a multi-factor investment platform, focusing on how to estimate stock and portfolio factor exposures. Stock exposures are derived from database values such as price-to-earnings and price-to-book ratios, then cleaned and…