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.
1,536 documents
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…
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…
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 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 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…
The document answers how to allocate weights across strategies in a multi-strategy backtest. Its proposed workflow is to extract each strategy’s daily return series and use an optimization package to find portfolio weights. This frames the task as portfolio…
The document describes a basic workflow for evaluating a trained quantitative model. After fitting the model on training data, apply it to a validation set, then compare its predictions with the observed values to assess performance. This separates model…
This research summary explains how to build a machine-learning stock-selection process using historical factor values to predict subsequent returns. In the training stage, a supervised model learns the relationship between inputs and returns; in the testing…
This brief coding question outlines a way to calculate fund performance statistics from a price series. It first derives periodic returns from price changes, then uses a performance-analysis library to compute cumulative return, annualized return, Sharpe…
The document summarizes CapTE, a model for predicting stock movements from social media text. A Transformer encoder extracts semantic features from posts, while a capsule network is used to represent structural relationships in the text. The approach is…
The document summarizes a study that develops a probabilistic classifier to identify high-frequency trading activity from intraday order data. Using French BEDOFIH market records, the researchers engineered features describing orders, including their prices,…
This forum post reports a suspected data-quality problem in a Chinese stock valuation dataset. The author observed that the September 14, 2022 snapshot appeared to contain more than 1,600 missing or erroneous records, while the adjacent dates seemed to have…
This report surveys several approaches to allocating across asset classes: macro and cycle-based fundamentals, mean-variance optimization, Kelly-CVaR, Black-Litterman, and risk parity. It describes a macro model that separates directional forecasts from…
This Chinese-language research digest summarizes two separate topics. The first reviews the United States target-date fund market, covering market share and flows, relative performance among fund series, and glide paths. It discusses glide-path averages and…
This document introduces mobile network activity as an alternative data source for quantitative investing. It explains that mobile devices continually exchange signals with cell towers and Wi-Fi access points, and that legally anonymized records may reveal…
This beginner tutorial uses the MNIST handwritten digit dataset to introduce TensorFlow through a simple image classification task. Each image has a digit label, and the model is intended to predict that label from the image. The tutorial chooses softmax…
This article challenges three barriers commonly associated with quantitative investing: needing advanced mathematical credentials, being able to code extensively, and having a large portfolio. It presents quantitative analysis as a way to use statistics and…
This guide explains simple and exponential moving averages as ways to smooth price series. An SMA averages prices over a selected window, while an EMA updates recursively and gives more weight to recent prices. It illustrates both calculations with a short…