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
This overview surveys six ICLR 2022 studies: periodic time-series forecasting, model-based policy optimization, disentangled representations, Stein-based sampling, deployment-efficient reinforcement learning, and training with privileged observations. The…
This article explains why selecting useful input features matters in predictive modeling. Irrelevant variables can add training time, contribute to overfitting, and make it harder for a model to generalize. Feature selection is presented as a way to reduce…
This forum post responds to a question about selling after a 10% gain or cutting a position after a 10% loss. The included example checks open equity positions against current prices, retrieves the highest price since purchase, and exits when price falls 7%…
This article describes a daily process for building a watchlist of strong stocks. After the close, rank shares by traded value and keep the top 30. From that group, look for stocks rising more than 3% on increased volume, giving extra attention to volume…
This Chinese-language article introduces a workflow for building custom stock-selection strategies on the older BigQuant platform. It contrasts platform-generated AI strategies, which learn from selected factors but may be difficult to interpret or tune,…
This study compares ways to hedge stock holdings, motivated by investors who hold equities as a base for IPO subscriptions and want to reduce exposure to price swings. It measures hedge costs using annualized futures discounts and compares those costs across…
This article explains how to assess a systematic futures model through test design and several complementary performance measures. It recommends testing across multiple instruments and long historical periods, and including commissions and slippage. The…
This article proposes studying Chinese A-share stocks during days when the broader market falls sharply. It suggests identifying historical selloff days, then examining two setups: stocks that close at the daily upper price limit despite the market decline,…
This document summarizes two external research papers. The first concerns allocating capital among private fund strategies within a fund-of-funds portfolio, using multi-objective linear programming to derive allocation weights. The second examines the ratio…
This article explains random forests and decision trees, then applies a random forest regressor to short-horizon Chinese stock selection. It describes bootstrap sampling, random feature selection, averaging tree predictions, tree pruning, regression split…
The document describes why quantitative investors use machine learning to analyze large datasets, forecast market direction, and select portfolios. It highlights the ability of these methods to represent nonlinear relationships and process data efficiently,…
This overview presents basic ways to assess broad equity-market conditions and limit portfolio exposure during potential declines. It describes moving-average crossovers as timing signals, with a shorter average crossing above a longer one treated as bullish…
This opinion piece presents stock trading as a possible independent career, emphasizing schedule autonomy, reduced dependence on an employer, access to shares in public companies, and the ability to shift attention among sectors. It argues that market…
This commentary argues that oversight of quantitative trading should focus on predictable, transparent market rules and enforcement of misconduct, rather than suppressing algorithmic methods as a category. It frames the regulatory challenge as balancing…
Risk parity allocates portfolio weights so that assets contribute more evenly to total portfolio risk, rather than assigning capital according to expected returns or equal dollar amounts. The document outlines a workflow: estimate asset volatilities and…
This review surveys three directions in factor investing: refining established factor methods, incorporating new data and models, and using factors as a basis for asset allocation. It describes improving value signals with multiple valuation measures,…
The document addresses a screening condition that combines a stock closing above a rolling maximum with a recent limit-up requirement. The questioner reports that the combined filters return no candidates even though individual conditions seem to identify…
The article introduces trend following as buying when prices rise and selling when they weaken, then reviews five indicators that may inform such decisions: moving averages, Bollinger Bands, MACD, RSI, and On-Balance Volume. It describes using price relative…
The report argues that ranking fund managers can reduce redundant information when one manager oversees several similar funds. It proposes tracking manager style across market capitalization, value versus growth, industry concentration, individual-stock…
This research summary presents cash-flow duration as a framework for understanding why equity characteristics such as value, profitability, investment, low beta, and dividend payout are associated with returns. Duration measures the timing of a company’s…
This brief review interprets the CSI 300’s movements through valuation bands tied to an assumed earnings growth rate. Using a 12-times valuation assumption and projected 2018 net profit growth, it describes an estimated index range and treats the July move…
This article presents a multi-asset allocation framework that combines traditional asset selection with allocation to systematic factors. It maps macroeconomic variables and style factors to asset classes, estimates exposures with time-series regressions,…
This research note discusses how to turn equity alpha signals into portfolio forecasts and combine multiple factors. It suggests converting factor z-scores into expected returns using average results from repeated cross-sectional regressions, and favors…
This research summary describes a machine-learning approach to predicting very short-term price changes from futures order-book data. It proposes using support vector machines with features such as best bid and ask prices and sizes, order-book depth, slope…