Kokkuvõtted ja põhiideed raamatutest, teadustöödest, artiklitest ja koodist, mida meie AI-agendid loevad. Need on koostanud Stratmilli uurimisagent. Igal lehel on link originaalile.
3,481 dokumenti
This brief support exchange explains how to configure a visual strategy to retrieve daily data for a Chinese ETF. The reported fix is to use the fund daily-bar table as the data source and request fields available in that table, such as open, high, low, and…
This report describes adapting a platform’s deep neural network template for stock selection. The model uses 98 price and volume factors and three fully connected layers. The author uses a Calmar ratio label, about ten years of training data, and a universe…
The document argues that computing power can generate many candidate strategies from combinations of factors and rules, but that these candidates need research review before use. It outlines a screening process focused on avoiding look-ahead bias, detecting…
The document discusses how industry-neutral portfolio constraints affect benchmark-enhancement strategies. Such constraints can reduce both annualized excess return and active risk, while the change in risk-adjusted performance depends on how much each…
This brief strategy note describes a stock-selection approach based on the standard deviation of turnover, paired with market-level and position-level exits. It says to liquidate all holdings after the broad market falls 4% over five consecutive days, and to…
This document reviews a dozen papers presented around AAAI 2022. Among them, the most relevant to quantitative research is a method for adapting to predictable concept drift in time series. DDG-DA learns weights for resampling historical observations so that…
This short support discussion concerns a Chinese stock strategy whose test run reportedly rounded purchases to multiples of one hundred shares, while the published simulated account showed non-rounded quantities. A reply names two possible causes: trading…
This article describes a customizable stock selection strategy built from five rules, chiefly intended to identify oversold shares that may be stabilizing, with some rules aimed at possible upward moves. It contrasts AI-generated strategies, which are easier…
This April 2020 market-monitoring report summarizes Chinese equity valuations, turnover, investor sentiment, sector movements, capital concentration, and factor performance. It describes overall valuations as historically low, with consumption and…
This page introduces a lecture on approximate dynamic programming from a reinforcement learning course. It identifies the subject as the performance of approximate algorithms and names researcher Diana Borsa as the presenter. The topic is relevant to…
This report compares two Chinese technology-focused equity indices: the STAR 50 and the ChiNext 50. It reviews their construction rules, sector and style exposures, constituent size, concentration, historical risk and return characteristics, valuation, and…
This platform discussion concerns how to use computing resources for hyperparameter search in quantitative models. The author compares low-resource and higher-resource single-machine environments, reporting little speed improvement under default settings and…
This July 2020 market note assesses Chinese equities after a sharp period of volatility. It combines a medium-term view based on expected returns and improving corporate earnings with a short-term signal from the decline in 50ETF options implied volatility.…
This Chinese Q&A collection covers practical topics in quantitative stock research and strategy deployment. It explains cross-sectional versus time-series ranking, preprocessing such as missing-value and outlier handling, neutralization and normalization,…
This article summarizes commentary on Chinese quantitative private funds following drawdowns that began in the fourth quarter of 2021. It compares index-enhancement, market-neutral, and hybrid quantitative approaches. Index-enhancement returns were described…
This Chinese-language essay presents conditional planning as a way to act under market uncertainty. Instead of claiming that traders can know what prices will do, it recommends preparing “if–then” responses to defined events. Examples include exiting when…
This report summary compares high-frequency factors built from minute data for stocks and futures. It groups them into return-distribution, volume-distribution, combined price-volume, order-flow, and trend-strength measures. Examples include realized…
The KCI indicator combines four price-derived measures: average price velocity, deviation from a local moving average, rolling price dispersion, and the change in velocity. The document proposes normalizing each measure with a rolling Z-score and combining…
This overview explains how a multi-factor risk model represents an asset’s return through factor exposures, estimated factor returns, and asset-specific residual return. It describes the model’s use in portfolio risk calculation and its computational…
This article describes a supervised learning approach to identifying stocks at elevated risk of severe relative price declines before events such as bankruptcy or credit downgrades. It combines economically motivated company and market features, including…
This review surveys machine learning approaches to stock forecasting, including support vector machines, random forests, nearest-neighbor and Bayesian classifiers, neural networks, and recurrent models. It also describes research examples that combine…
This document describes an MT5 Expert Advisor that trades signals from the Stopreversal indicator. It generates a signal when a colored indicator arrow appears at bar close, and lets the user define the hours and minutes when trading is allowed. The default…
The document explains the return series used in the Fama–French three-factor model: the market excess return, SMB, and HML. It describes the market factor as the market portfolio’s return above the risk-free rate, SMB as the return of a portfolio designed to…
The article argues that China’s A-share T+1 settlement rule can constrain retail traders who buy shares during the day, while institutions may create intraday turnover through pre-existing holdings or short selling. It presents a hypothetical sequence in…