สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,481 รายการ
The document summarizes research on time-series intraday momentum in US equity ETFs. It describes a signal in which the first half-hour return, measured from the prior close, predicts the final half-hour return in the same trading day. Using SPY data, the…
The document introduces attention and Transformer components, then adapts them to forecast stock returns from factor sequences. Its proposed architecture adds Time2Vec features to factor inputs, applies self-attention and encoder layers, and uses a…
This article develops an A-share stock-selection framework around earnings surprises and post-earnings-announcement drift. It groups surprise signals by whether new information comes from analyst revisions, reported fundamentals versus analyst expectations,…
This Chinese-language forum post addresses how to identify, for each stock, the day with the greatest trading volume in a prior window and retrieve that day’s closing price along with the previous day’s close. It outlines a windowing approach: shift the data…
The paper constructs a monthly measure of fear of missing out from three weighted components: a short-term versus long-term moving-average spread, Google search activity for FOMO-related terms, and investor margin-account use. It examines the index over 2004…
This essay defines quantitative investing as using mathematical methods, data, and factors to guide security selection and trading. It groups approaches by time-series versus cross-sectional decisions, by signal source such as price and volume factors or…
The note describes a way to turn high-frequency trade data into a daily measure of stock order book pressure. It uses intraday tick price movements to identify displayed orders above and below traded prices, aggregates these observations at the close, and…
This report summary outlines the structure of the U.S. retirement system and the investment choices available through employer plans and individual retirement accounts. It describes these arrangements as part of a broader retirement landscape and notes that…
The document explains how to bring financial statement and macroeconomic data into a quantitative model as features. It distinguishes macro data, which is readable from the platform but must first be aligned and merged with the sample data, from financial…
This overview explains statistical arbitrage as a family of strategies that trade relative mispricing across related instruments. It distinguishes cross-market, cross-asset, ETF, and market-neutral approaches, and gives pairs trading as a central example:…
This event study examines how Chinese convertible bonds and their underlying shares behave around conversion, early redemption, and conversion-price resets. It reports that conversions increase share supply and can weigh on the underlying stock. Early…
This research digest reviews two portfolio topics. The first concerns Shiller’s cyclically adjusted price-to-earnings ratio (CAPE): it can help forecast long-run equity returns as valuations tend to mean-revert, but its short-term signal is unreliable when…
The article describes a daily, long-only ETF rotation system that applies a five-day and a 42-day closing-price moving average to each asset. Crossovers generate buy and sell decisions, while available capital is allocated equally among positions with buy…
This report discusses fixed-amount periodic investing in funds as a way to align contributions with investor cash flows and reduce the pressure to time volatile equity markets. It distinguishes investing an existing balance from investing new contributions…
This brief platform support exchange distinguishes missing feature values from NaN values produced by calculations. The support response says missing values had already been filtered; remaining NaNs were calculation results, such as an undefined zero divided…
This event-driven equity strategy buys stocks at the open after financial results are announced, selecting companies whose year-over-year net profit attributable to parent shareholders has grown by more than 30%. Eligible stocks are ranked by growth, and the…
This educational article explains a crypto bubble as a rapid price rise driven by investment enthusiasm and expectations of quick gains, followed by the possibility of a sharp decline. It attributes bubble formation to new investors, fear of missing out,…
This report examines whether removing stocks selected by high-frequency multi-factor short portfolios can improve a CSI 300 index-enhancement strategy. It compares three approaches: combine standardized factor scores, use a regression model to forecast…
This article describes five technical patterns that it presents as warnings of a possible stock market top: an accelerating large bullish candle, a shooting star, a high-wave candle, a hanging-man candle, and high-volume sideways trading after a rally. It…
The document describes a Chinese equity screening idea that combines three filters: membership in the metaverse concept group, a positive institutional-flow signal, and an upward or positive DEA reading. It frames the first filter as a sector selection, the…
This Chinese-language article introduces order flow toxicity through the market microstructure problem of information asymmetry. Informed traders may profit at liquidity providers’ expense; if this adverse selection becomes severe, market makers may withdraw…
This Chinese-language article introduces a customizable stock-selection strategy on a quantitative trading platform. It describes combining five selection rules, mainly intended to find stocks that have fallen sharply and begun to stabilize, with some rules…
This document presents the Ppv technical indicator, which uses closing, high, and low prices over a chosen lookback period to derive a midpoint and six price levels. Three levels are labeled as resistance and three as support in the indicator’s formula…
The document explains how to build a fund backtest in a platform whose standard workflow does not directly support fund data. The example strategy buys when a short moving average crosses above a longer one and sells when it crosses below. It describes…