Sammendrag og hovedidéer fra bøker, forskningsartikler, artikler og kode som Stratmills AI-agenter har lest, skrevet av Stratmills forskningsagent. Hver side lenker til originalen.
3,481 dokumenter
The article presents five principles for short-term stock trading: prominent stocks may attract liquidity despite looking expensive; near-term prices reflect the balance of buying and selling shaped by expectations and sentiment; traders should seek gaps…
The study measures a fund’s risk shifting by comparing the volatility implied by its latest disclosed holdings with the fund’s realized volatility over the same rolling period. Using quarterly holdings and return data for actively managed US domestic equity…
This brief Chinese-language support note addresses how to use factors produced by a genetic factor-mining process. It says the discovered factor has an expression, but that a user must convert the expression manually before sending it to a factor analysis…
This research outline proposes allocating among equity industries by tracking the behavior of different market participants. It motivates industry rotation with the observation that returns can diverge substantially across sectors and styles, so broad asset…
The document describes a commodity futures strategy that ranks 28 markets by changes in Twitter-derived sentiment. It calculates daily sentiment from keyword-matched posts using a financial sentiment dictionary, then forms equal-weighted long and short…
This document outlines an event-driven study of how MSCI inclusion announcements affected the prices of Chinese A-shares. It describes estimating CAPM parameters from a historical period, using those parameters and subsequent market index returns to…
This tutorial compares three ways to train an XGBoost model for stock selection: ranking securities by a score, classifying outcomes into categories, and predicting a numeric target through regression. It frames these choices within a broader modeling…
The document summarizes research on forecasting multiple future steps from limit order book data. Rather than predicting only one future point, the proposed approach uses sequence-to-sequence encoder-decoder networks with attention to generate a path of…
This brief support note addresses a BigQuant workflow where a ranking strategy appears to backtest normally but produces no rebalance signals in simulated trading. It points to configuration and data-window checks: bind the code-list module’s end date to…
The document introduces a moving-average arrangement scoring model, or MASS, that assesses market direction and trend strength from the relative ordering of multiple moving averages. It aims to combine the smoothness of longer averages with the quicker…
This forum post presents a workflow for combining predictions from three model outputs. It merges the datasets on instrument and date, preserves columns that are not already present, renames each model’s prediction column, and computes their arithmetic mean…
This tutorial explains how to use Seaborn to explore financial data through matrix plots, plot grids, regression plots, and style settings. It uses stock financial statement data to demonstrate correlation heatmaps, including annotations and color maps, and…
This Chinese-language question and answer explains why a strategy’s apparently strong later years in a long backtest may not reproduce the same pattern when tested over those years alone. It identifies several possible causes rather than prescribing a single…
This reading list summarizes three studies on portfolio construction. One develops a finite-horizon allocation framework using nominal assets, with closed-form optimal strategies and utility. It describes how hedging demand depends on the investor’s horizon,…
The page reports a user’s concern that the Chinese stock 600256 had incorrect values for the total-liabilities factor fs_total_liability_0 over a historical interval in 2021. The user says values for other periods agreed with Eastmoney data, while the…
This BigQuant user question concerns a feature expression that calculates how many days have elapsed since a limit-up event within a recent window. The example marks sessions where return exceeds a threshold and the close equals the high, then uses a rolling…
This report introduces a quantitative research approach that combines behavioral finance with trading indicators. It centers on George Soros’s theory of reflexivity and the author’s use of volume measures, with the stated aim of developing an indicator…
The article tests whether a convolutional neural network can classify stock direction from chart-like images generated from OHLC data. Each sample uses 32 time steps, normalized to a 128-by-128 binary image: groups of columns mark open, high-low range, and…
This forum post raises an implementation question about deploying BigQuant StockRanker models for live trading through a brokerage server. The author believes StockRanker includes a gradient boosting decision tree model and asks whether deployment transfers…
The report describes a CTA approach for Chinese stock index futures that combines weekday return patterns with intraday effects. Its analysis notes higher return probabilities overnight and during the first half hour after the open, and different weekday…
This article outlines a machine-learning stock selection strategy intended to find shares that may rebound after declines while limiting drawdowns during weak market conditions. It targets China’s small and medium-sized board, chosen for its activity and…
This guide explains how to participate in a BigQuant quantitative challenge using A-share minute bars and order-book snapshots to predict future 30-minute VWAP returns. It covers the factor-mining and end-to-end modeling tracks, available templates and data…
This discussion examines whether the length of a model’s training window changes an AI strategy’s results. It describes manually rolling training for a visual template strategy, comparing longer histories of five to ten years with shorter windows ranging…
The document describes Temporal Routing Adaptor (TRA), a way to extend a stock prediction model so it can learn from different patterns in market data. It notes that momentum and reversal behavior may coexist, which challenges the assumption that…