Kokkuvõtted ja põhiideed raamatutest, teadustöödest, artiklitest ja koodist, mida meie AI-agendid loevad. Need on koostanud Stratmilli uurimisagent. Igal lehel on link originaalile.
3,481 dokumenti
The document shows a stock-ranking workflow that derives 30-day and 90-day returns, ranks securities cross-sectionally, filters the universe, and creates a forward-return label for model training. A StockRanker module trains on historical data and predicts…
This discussion presents a daily Chinese A-share small-cap strategy that filters stocks by listing age, valuation, and turnover rank, sorts the candidates by market capitalization, and targets a basket of twenty names. Its rebalance handler identifies…
The article describes a stock selection experiment in which a machine learning model used only days since listing. Its reported backtest showed positive returns, though with high volatility. The authors attribute performance partly to a rising market during…
This Chinese-language article outlines a six-step process for developing stock selection rules: find an idea, define its logic, run an initial backtest, tune parameters, check for overfitting, and select strategies for combination. Its example setups look…
This study summary examines active-trading (ACT) factors in Chinese equities, which distinguish aggressive from passive executions and group activity by trade size. It argues that the undivided ACT factor has weak stock-selection power, then splits…
The report studies how equity factors behave across groups of A-share stocks sorted by price amplitude, using ten groups from lower to higher amplitude. It reports that price and volume factor effectiveness rises as amplitude increases, while fundamental…
This page summarizes a lecture on multi-step and off-policy algorithms in reinforcement learning. It identifies the subject as methods that learn from sequences of rewards across multiple steps while handling data generated by a policy different from the one…
This document outlines four indicators that combine price and trading volume: the Money Flow Index (MFI), On-Balance Volume (OBV), Price Volume Trend (PVT), and a simplified OBV variant called SOBV. MFI compares rolling positive and negative money flows,…
This short assignment response defines quantitative investing as turning a personally developed set of screening and trading rules into a computer-executable process. It presents rule design and implementation as the core idea: formulate conditions for…
This submitted assignment defines quantitative investing as making investment decisions with mathematical and statistical analysis, historical data, and computing. It describes several practical advantages: processing large datasets, applying rules…
The report describes an AI-based score for assessing intraday trading opportunity in Chinese stocks and broad indices. Using 20 trading days of one-minute returns, it compares observed returns with randomly constructed return sequences. A higher score…
The document introduces covariance as a measure of how two variables vary together, defining it through the expected product of each variable’s deviation from its mean. Positive covariance indicates a tendency to move in the same direction, while negative…
This technical note presents the MEJT indicator as a price-action rule built from high, low, and close data. Its buy condition checks whether the current high exceeds the prior high, the close exceeds a high from two periods earlier, and the close lies…
This research summary explores stock-selection signals built from Level 2, trade-by-trade data. It classifies trades by order size and direction, then constructs measures such as the share of trading represented by different order categories and net buying…
This report summary presents a factor model for ranking managers of Chinese public equity and equity-oriented hybrid funds. It builds a manager-level investment index by weighting the funds each manager oversees by fund size, then evaluates candidate…
The document summarizes research on whether company managers’ tone in financial communications predicts equity returns. It describes building a sentiment index by applying text analysis to corporate reports and earnings-call transcripts, then comparing its…
This report summary outlines a fixed-income-plus-equity portfolio design in three stages: strategic allocation, tactical timing, and capital management. Strategic weights are set with a mean-variance model using broad equity and bond indices, with periodic…
This Chinese Q&A explains why a genetic programming factor-mining workflow can report factors that pass a test yet return an empty factor collection. The answer says the run log shows that the global fitness test did not pass, so no factors were retained. A…
This guide lists reasons a submitted quantitative factor may fail to produce an evaluation score. It recommends checking factor-analysis output on the designated dataset before submission and verifying that a machine-learning model completed training and…
The document summarizes research that classifies corporate bond funds as liquidity demanders or suppliers according to how their trades align with dealer inventory cycles. Using TRACE transactions and fund holdings, the underlying study infers inventory…
This introductory explanation describes how a convolutional neural network turns an image into a class prediction. A filter slides across local pixel regions to produce feature maps; filter count, stride, and zero padding affect the maps’ depth and…
A BigQuant user reports that a stock AI strategy template fails with an index error when its prediction or backtest date range includes January 1, 2016. The issue is described as intermittent and associated with using certain factors. The suggested…
This Chinese-language discussion addresses a backtest display that continues to list a stock after an order targets a zero portfolio weight. The listed position has a quantity of zero, which can look like an unsettled holding or a bookkeeping defect. The…
This short note outlines a way to represent the cost basis of stock holdings across market participants. It proposes estimating average holding cost by weighting transaction prices by traded quantities, then using daily costs and trading volume to estimate…