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.
3,481 documents
The example code implements a simple long-only threshold strategy for one security. It opens an initial position, then compares each close with the most recent recorded purchase price. A decline beyond the configured buy threshold adds another purchase; a…
This document outlines a simplified Merrill Clock approach that classifies economic conditions using the direction of year-over-year GDP and CPI changes. It applies moving averages to reduce short-term noise and delays the economic data by one period in…
This short platform guide explains how to limit the prediction or validation stock universe in a visual AI stock selection workflow to a chosen concept sector. It instructs users to insert a shared module for selecting stocks from a specified concept sector…
This strategy description outlines a daily MACD crossover system for Kweichow Moutai shares. It buys when the fast MACD line crosses above the slow line and sells when the slow line crosses above the fast line. The stated setup uses daily stock bars, starts…
This discussion explains when stock universe filters should apply to both model training data and prediction data, and when they might be applied only at trading time. Its general recommendation is to use the same data processing in both sets. Filters that…
This report examines whether mainland China’s northbound investor flows can inform A-share trading. It tests flow thresholds for market timing, ranks sectors and stocks by net inflows, and combines sector selection with stock selection. The timing approach…
This forum post asks how to test high-frequency equity factors built from minute bars. It cites examples from a China International Capital Corporation multi-factor series: the average squared correlation between the high and low prices of 50-minute bars,…
This brief Chinese-language assignment submission argues that factor quality matters more than the choice of predictive model: a strong factor is presented as the foundation of a strong strategy. It says the author ran a linear-regression strategy because…
This essay argues that traders who blame quantitative funds for losses may overlook weaknesses in their own discretionary process. It identifies three recurring pitfalls: emotional decisions, overgeneralizing from vivid stories or isolated winners, and…
This midyear financial engineering report reviews China’s equity market through the first half of 2020 and frames its outlook around two themes: timing the market by following trends and reviewing factor-based stock selection. Its summary describes a gradual…
The document outlines a quantitative approach to forming a daily market outlook. It compares the current broad-market setup with similar historical situations, drawing on more than ten years of past market data, and uses the subsequent behavior of those…
The document discusses constructing supervised-learning targets from daily Chinese stock data. Its SQL example derives a forward return from later prices, clips extreme values using the first and ninety-ninth percentiles, and selects dates, instruments, and…
This report studies whether company patent data can help predict stock performance. It compares factors based on patent counts and types, including invention patents, utility models, and design patents. The report treats granted invention patents as the most…
This forum post flags a data-quality concern in the net profit year-over-year growth field for Beijing Stock Exchange listings. The author reports substantial differences between the values from two named market-data sources and shows many securities with a…
The document introduces the Demarker indicator and gives its calculation over a configurable lookback period. For each bar, it records only upward changes in the high relative to the previous high, and only downward changes in the low relative to the…
The document explains VeighNa's standardized datafeed configuration and lists supported providers, their broad instrument coverage, and available data frequencies. Configuration uses a provider name and credentials, with a token placed in the password field…
This support exchange compares a median absolute deviation (MAD) clipping calculation with a platform's outlier-removal module. The example method computes a series median, finds the median absolute distance from that value, and clips observations to bounds…
The document summarizes Chinese equity research on refining a traditional idiosyncratic volatility factor. The baseline measure is built from a Fama–French three-factor model. The report links volatility clustering in individual stock returns to persistence…
This overview explains automated trading as the use of software to generate or act on trading instructions, place orders, and manage positions with varying degrees of human involvement. It outlines a basic workflow: configure a platform, define entry and…
This screen selects stocks in the metaverse theme whose indicated 9:25 price change is below 6% and whose weekly price crosses above a 30-week moving average. The document presents the theme as a way to focus on a current market segment, the early-session…
This Chinese equity-market report uses distance from each stock or index’s highest closing price over the prior 250 trading days to monitor trends and identify potentially leading industries. It counts stocks that reached a 250-day high during the latest 20…
The post explains Stochastic RSI as an RSI series normalized against its recent range, then smoothed to produce a fast line and a signal line. It relates common naming conventions: the fast %K line corresponds to the Stochastic RSI output, while %D…
This introductory article explains overfitting as a model learning quirks in its training data instead of patterns that generalize. It contrasts strong training performance with weaker results on unseen observations, using a résumé screening example, and…
This research summary examines the ChiNext 50 index through the supply chains of its constituents, arguing that sector weights alone miss how technology firms connect to suppliers and customers. It describes the index as concentrated in technology, with…