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 summary of a Chinese A-share research report explains small-cap and value premiums through stocks’ differing sensitivities to cash-flow expectations and discount rates. It frames equity returns with a two-beta model that separates those influences,…
This article describes a strategy that changes exposure to equity factors according to a four-state business-cycle classification: recovery, expansion, slowdown, and contraction. It combines the US Leading Economic Indicator with a Global Risk Appetite Cycle…
This study examines Bitcoin risk using high-frequency returns and realized variance, with particular attention to jumps and their role in forecasting. It finds that conventional jump measures can be biased by frequent, extended price moves. Threshold-based…
This document summarizes an article on applying quantitative methods to environmental, social, and governance investing. It argues that quantitative portfolio tools can translate investor preferences into portfolio construction and extend sustainability…
This 2020 research summary assesses when reported global COVID-19 cases might peak and whether China could face another major outbreak. It argues that expanded testing could first reveal a turning point in daily reported cases as backlogs clear, while…
This document outlines a daily MACD strategy applied to five named Chinese stocks. It describes buying when the MACD fast line crosses above the slow line and selling when the slow line crosses above the fast line. The listed securities span consumer goods,…
This advice article presents four habits for more disciplined stock trading: record trade ideas and their reasons, wait for clear opportunities, manage emotions, and control position size. It recommends reviewing outcomes to identify recurring strengths and…
This 2019 outlook reviews China’s financial product and asset management markets amid regulatory change. It argues that rapid market expansion had already slowed before the new asset management rules, with aggregate assets contracting in 2018. The report…
This report studies whether the stability of intraday trading patterns can help rank Chinese stocks. It calculates seven measures from five-minute returns and volume, including volatility, skewness, kurtosis, and a volume concentration index. To account for…
This forum post presents a Chinese A-share strategy built from the Pearson correlation between each stock’s one-minute closing prices and trading volumes over a day. It sums the daily correlation factor over a rolling five-day window, then ranks stocks by…
This article reviews an empirical study of whether skilled active equity fund managers perform differently when investor sentiment and noise trading are elevated. Using US domestic active equity mutual funds from 2002 to 2014, the study estimates rolling…
This report explains why common equity factors may need adjustment for banks. Large cash and financial asset balances complicate comparisons of liquidity, while provisions and reserve practices can distort earnings multiples. Some operating measures used for…
The article explains why feature selection can reduce irrelevant or redundant inputs while preserving a model’s predictive ability. It illustrates the idea with a water park ticket-sales example, using weather, ice cream consumption, coffee consumption, and…
This support discussion concerns a simulated trading strategy that reportedly generated no signals after submission. The response says the shared strategy link could not be accessed and asks for a link created through the development environment’s sharing…
The document explains why conventional random or K-fold cross-validation can mislead when tuning models on time-series data. Because observations are ordered and related, a random split may train on later periods and validate on earlier ones, allowing future…
This document outlines the Directional Movement Index (DMI) calculation from high, low, and close prices using a configurable lag. It first derives a smoothed true-range measure from the current bar's range and gaps relative to the previous close. Upward and…
This research note proposes a stock-selection factor based on the trend in quarterly gross profitability. It estimates the trend as the time coefficient in a linear regression, using either sequential-quarter or year-over-year observations. The study…
This brief learning response outlines a basic way to formalize an existing stock-picking approach: screen companies using measures such as price-to-sales, price-to-earnings, year-over-year profitability, and market capitalization, then apply a timing process…
This BigQuant workflow illustrates a daily Chinese equity ranking process. It prepares stock features from price and prefactor data, including lagged returns and volume ranking, then creates a supervised label from a clipped forward return. Training data is…
The article explores using an LSTM neural network to forecast five-day returns on the CSI 300 and use the forecast as a market timing signal for a separate stock-ranking strategy. It describes feeding the model 30 days of standardized open, high, low, close,…
This brief guidance note outlines ways to improve performance in a quantitative trading exercise that processes large datasets. It asks whether Python loops are the best choice for large-scale work, and points readers toward pandas operations designed to…
This Chinese-language summary introduces a research paper on factor timing, which combines ideas from market timing and factor investing. It frames the theoretical argument around the stochastic discount factor (SDF), assuming a conditional factor model can…
The article proposes a buy-side strength factor from minute-level order-book data. It combines price and displayed quantity at each of the first five bid levels, does the same for the first five ask levels, and forms a ratio of the bid-side total to the…
The article explains how a long short-term memory network can use sequential market data for short-horizon stock selection. It outlines LSTM’s forget, input, and output gates, then describes a model with an LSTM layer, dropout, and a dense layer. The model…