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.
5,922 documents
The document explains a portfolio construction approach that forecasts stock trading volume and uses the forecasts as a proxy for expected price impact. With trade size held fixed, lower volume implies a higher participation rate and greater expected impact,…
The document explains alpha as the return remaining after comparing a portfolio’s actual return with the return predicted by the Capital Asset Pricing Model. It gives the formula using portfolio return, the risk-free rate, portfolio beta, and benchmark…
This document outlines a forecast of constituent changes for four major mainland Chinese equity indices: the CSI 300, CSI 100, SSE 180, and SSE 50. It explains the potential trading relevance of index rebalancing: when funds tracking an index must adjust…
This configuration specifies a Qlib workflow for training a CatBoost model on Alpha158 features for the CSI 500 universe. The data spans 2008 through mid-2020, with training through 2014, validation during 2015–2016, and testing from 2017 onward. The model…
This meetup listing raises two quantitative research questions: why factors with strong information coefficients and information ratios may produce weaker Sharpe ratios, and why combining individually strong Sharpe-ratio factors can reduce portfolio…
The guide distinguishes portfolio profitability from the profit and loss history of individual trades. Portfolio profitability is calculated by valuing configured tradable assets in the selected reference market, then comparing the total value at OctoBot…
This strategy rotates between an equity fund and a government bond fund by comparing their returns over the prior quarter. At each quarterly decision point, it invests fully in whichever asset had the higher return during the ranking period, then holds that…
The strategy ranks 20 industries each month using the market-cap-weighted average of each constituent stock’s current price divided by its trailing 52-week high. It buys stocks from the six highest-ranked industries and shorts stocks from the six…
This forum post documents a BigQuant workflow in which LightGBM finishes running, but the subsequent score-to-position step fails because its query orders predictions by a column named score that is absent from the input dataset. The error identifies the…
This configuration describes a Qlib workflow for training a Localformer model on China A-share data and evaluating its predictions as a portfolio signal. It uses the CSI 300 universe and benchmark, an Alpha360 data handler, robust feature normalization,…
This research summary explains how turnover controls affect portfolio construction and factor evaluation. Portfolio weights change as risk estimates and expected returns change, while portfolio constraints and relative stock performance can impose a minimum…
This Chinese equity screen selects stocks associated with the robotics concept, with turnover between 3% and 12%, circulating market value below 10 billion, and a stated scale threshold above 200 million. The post says the added scale filter is intended to…
The document defines maximum drawdown as the largest decline from a historical net asset value peak to a subsequent trough within a selected period. It frames the measure as an estimate of the worst loss an investor might have experienced after buying a…
The document describes three equity strategies built around a bull-bear indicator: a direct timing rule for broad indexes, monthly indicator-change rotation among industries, and index allocation based on the share of constituent stocks signaling a long…
This article proposes ListFold, a listwise learning-to-rank loss for factor-based long-short equity strategies. Its central design treats the top and bottom of a predicted stock ranking as equally important, so one coherent ordering can select both long and…
The article explains how liquid factor portfolios can approximate some hedge fund returns, potentially offering an accessible, lower cost substitute for investments with limited liquidity, high fees, or high entry barriers. It reviews linear multifactor…
This weekly report reviews Chinese market conditions and fund activity, with particular attention to plans to include exchange-traded funds in the Stock Connect program and the approaching release of restrictions on shares in the first public REITs. It also…
This research summary describes a monthly industry rotation method built from price and volume behavior. It groups candidate signals into six categories: momentum, trading volatility, turnover, long-short comparison, price-volume divergence, and alignment…
The document outlines four portfolio approaches: a calendar effect fund of funds (FOF), a performance enhancement FOF, a fund size undervaluation FOF, and a core-satellite ETF portfolio. The calendar strategy selects five active equity funds equally using…
This research summary describes using an imitation portfolio to infer the holdings of three Chinese mutual funds. The motivation is that public disclosures arrive with a delay and represent holdings at reporting dates, making them an imperfect guide to a…
This research summary presents a framework for timing equity factors whose returns have become less reliable. It reviews indicators such as valuation spreads and pairwise correlations, and examines their relationship with future factor returns. A random…
This survey introduces regression methods used in financial modeling, from ordinary linear models to polynomial and logistic regression. It also explains quantile regression for examining different parts of a conditional outcome distribution, including its…
This research summary presents factor timing as a risk-control problem rather than solely as a forecast of factor returns. In a multi-factor portfolio, the approach adjusts upper and lower bounds on factor exposures. Those bounds are tied to factor risk,…
This Chinese equity selection recipe combines three filters: return on equity above 6% in each of the prior two years, high dividend yield, and net inflows attributed to major market participants. It also excludes stocks that closed at the daily price limit…