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
This example builds a macro ETF portfolio through several AI roles: agents assess growth, inflation and rates, debt and liquidity, and challenge one another’s conclusions. A trading agent then combines their views into a diversified basket drawn from equity,…
This Chinese-language forum post asks how BigQuant’s StockRanker model works and whether its gradient-boosted decision tree component could be replaced with another ensemble method, such as XGBoost, while retaining a similar ranking strategy. It describes…
This research examines how crude oil returns relate to the Chinese equity market and industry returns, then applies estimated oil sensitivity to stock timing, industry rotation, and portfolio risk control. It describes a changing economic relationship:…
This document describes a Chinese equity screening approach that combines price movement, short-term trend, ownership concentration, and market capitalization. It selects stocks with daily amplitude above 1, prices above the five-day moving average,…
The document presents a process for identifying stocks linked to an investment theme using company business classifications and supplier relationships. It starts with leading firms tied to the theme, finds their shared business activities and common…
The document presents a process for identifying stocks linked to an investment theme using company business classifications and supplier relationships. It starts with leading firms tied to the theme, finds their shared business activities and common…
This Qlib configuration describes a machine-learning workflow for ranking CSI 300 stocks. It uses the Alpha360 data handler and a double-ensemble model built from gradient-boosted trees. The configured label is a forward close-price return, while the…
This document is a QuantStats tear sheet for a strategy labeled citadel-luna, compared with SPY over January 4–15, 2026. It reports a 2% strategy total return versus 1% for the benchmark, with a maximum drawdown near 0.7% for both. The strategy’s reported…
The author investigates whether the highest-ranked stocks from a convolutional neural network strategy deliver the best results. The experiments apply a model trained on a small number of stocks to broader selections, then backtest separate groups of ranked…
This document is a short summary of a report about constructing a fund-of-funds portfolio that can consistently outperform the median actively managed equity fund. It highlights the difficulty of selecting funds that remain above that benchmark across…
The document summarizes an analysis of the China Strategic Emerging Industries Index and its associated ETF. The index selects 100 listed companies from areas such as environmental technology, information technology, biotechnology, advanced manufacturing,…
This algorithmic implementation describes an annual asset-growth factor strategy for U.S. equities. At the end of June, it calculates each eligible company’s change in total assets from the prior observation, sorts stocks into ten groups, buys the…
The document surveys ways to revise investment strategies, including changing asset allocations, rebalancing, diversifying across assets, adding quantitative signals, and strengthening risk controls. It mentions tools such as value-at-risk, risk budgeting,…
The article introduces three areas of decentralized finance beyond lending: staking, asset management, and insurance. It explains how proof-of-stake networks reward validators for locking tokens, how delegation can let smaller holders participate, and how…
The document explains the Kelly criterion as a way to choose leverage and distribute capital across trading strategies to maximize long-run compound growth. Under assumptions of stable return means and standard deviations, normally distributed returns,…
The document describes a U.S. equity size-factor strategy that ranks stocks by market capitalization and takes opposite positions in the smallest and largest groups. Its stated research framing uses deciles, while the QuantConnect implementation limits the…
This study examines whether stock-selection factors earn premiums from choosing stocks within industries, allocating across industries, or both. It tests 21 definitions spanning value, quality, momentum, low volatility, and size, using global…
The article evaluates a deep-learning stock-ranking model across broad-market and filtered Chinese equity universes. It uses rolling windows of three years for training and one year for evaluation, then compares portfolio sizes, rebalance intervals,…
This research outline proposes constructing an A-share stock portfolio that seeks exposure to alpha while limiting unstable style exposures. Its motivation is concern that alpha-hedging returns may track market style rotations and that strategies experienced…
This introductory article defines quantitative investing as using numerical models and systematic rules to guide investment decisions. It contrasts model-based methods with more discretionary approaches, then describes claimed benefits: disciplined…
This study examines how factor exposure limits affect optimized portfolios built around the CSI 300 and CSI 500 indices. It reports that raising the limits can increase excess returns, drawdowns, and tracking error, so the change in return relative to the…
This overview explains beta as an asset’s estimated sensitivity to one or more return factors, usually a market index, using linear regression. It describes hedging as taking offsetting positions to reduce an identified risk exposure, then outlines…
The report describes a sector-rotation framework that pairs quantitative clustering with macroeconomic reasoning. It first groups industries using features such as returns across market conditions, return on equity, and revenue growth, then makes limited…
This article presents forecasts for wider cryptocurrency use and argues that institutional participation could expand alongside retail adoption. It cites research projecting that crypto users could reach one billion by 2030, alongside a separate estimate…