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 describes eight groups it presents as influential in China’s A-share market: foreign investors, short-term speculative funds, social security and insurance funds, securities firms’ proprietary desks, corporate insiders, public funds, and…
This forum post reports a disagreement in 24-period and 72-period moving averages for a market series on a specified date. The author compares values from two retail charting sources with results from a quantitative platform, noting that the two external…
A user reports that every label in a trading demo appears to be zero. The response explains that the platform’s visualization shows only a subset of the data, and the displayed rows may all happen to carry the zero label. It recommends inspecting the full…
The document outlines why quantitative investors use machine learning to analyze growing financial datasets, forecast market movements, and help select portfolios. It describes machine learning's capacity to represent nonlinear relationships and process data…
This overview describes Chan theory as a chart-analysis framework built from nested price structures. It moves from processed candlestick fractals to strokes, segments, and overlapping consolidation zones, then classifies larger moves as advances, declines,…
This meetup Q&A covers several practical quantitative trading topics. It explains rolling training as repeatedly updating a model using a moving or expanding historical window, and distinguishes incremental updates from retraining on the full dataset. It…
The document summarizes a research paper that uses a neural network to produce portfolio weights for exchange-traded funds. Instead of forecasting expected returns and then feeding those forecasts into a conventional optimizer, the approach directly tunes…
This Chinese-language seminar summary frames AI adoption as a response to falling asset-management margins despite growing assets under management. It sketches a progression from adjusting active portfolios using factor analysis, to building long-short…
This study outlines a Deep Q Network approach to timing trades in one stock. Instead of storing action values for every possible market state in a table, a neural network estimates values for available actions. The agent stores state, action, reward, and…
This report proposes diversifying portfolios across market, style, and strategy risk premia rather than allocating only among broad asset classes. It uses representative global equity, bond, and commodity indices to construct long-only strategies reflecting…
This introduction explains the Skip-gram model as a method for predicting nearby context words from a chosen center word. It uses a short example sentence and a window extending two words to either side. The explanation defines one-hot representations, dense…
This article presents volume as a way to assess the force behind price movements. It argues that record volume alone should not be treated as proof of a market top, since trading activity can continue to set new highs. Instead, it singles out expanding…
This review summarizes historical evidence on how assets and active strategies performed during periods of high and rising inflation in the United States, United Kingdom, and Japan. It defines inflation episodes using accelerating year-over-year inflation…
This analyst note reviews a Chinese bank IT provider’s 2019 results and argues that its business is shifting toward financial technology software and services. It reports revenue growth, a sharp increase in net profit, and software and technology services…
This study examines whether a third-party platform’s rapid redistribution of sell-side analyst upgrades and downgrades changes price discovery and the value brokers provide to clients. Using US recommendation data from 2009–2013, leak timestamps, intraday…
This article introduces one-dimensional convolutional neural networks as a way to process financial sequences. A convolution applies shared filters across local time windows, allowing the model to learn patterns that can appear at different points in a…
The document offers a brief allocation recommendation for bond funds in a period of increasing credit risk. It advises favoring funds with higher credit scores and specifies a threshold of 2.7 or above according to the authors’ credit scoring table. The…
This document is available here only as a Chinese-language title and outline, with the body represented by a link to a PDF. The outline describes a quantitative approach to asset allocation that separates strategic allocation from tactical allocation. It…
This document outlines an asset-allocation approach that separates asset selection from portfolio weighting and market timing. It explains a hidden Markov model as a way to infer unobserved market regimes from observable data, represent complex observations…
This article explains how to configure an older BigQuant workflow to analyze alpha expressions in a manner modeled on WorldQuant’s WebSim. Users specify a factor expression and set the stock universe, data delay, linear decay, market or industry…
This brief troubleshooting exchange addresses a quant model that fails when configured with a single factor, even though the factor values appear normal. The proposed fix is to assign the factor a shorter alias; the author reports that using a very brief…
This BigQuant support note addresses a strategy that can read an uploaded CSV during development but fails to access it after being launched in simulated trading. It recommends storing the data as a platform data source and loading it within the trading…
This brief BigQuant support note explains why a cloned strategy can work in backtesting yet fail in simulated trading. The example strategy was designed only for backtests, so its date range and instrument reference need changes before simulation: bind the…
This research summary argues that standard single-factor information coefficient tests may not reflect index-enhancement practice. A factor’s performance in a broad shared universe may not transfer to a benchmark’s eligible stocks, and simple tests may omit…