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 reviews research on whether investor sentiment helps explain stock return anomalies or appears predictive because of spurious regression. Persistent predictors can seem to forecast returns in finite samples when expected returns also vary over…
This research summary examines high-frequency equity factors built from minute bars, tick data, and transaction-level records. The factors capture intraday skewness, downside volatility, reversals, late-session trading, price-volume relationships,…
This brief exchange explains how to exclude Beijing Stock Exchange listings when labeling Chinese A-share stocks with a default template. It recommends using an A-share filtering module or adding a custom Python filter to the workflow. The suggested…
The report treats corporate events as equity style factors and evaluates them within a multi-factor research framework. It describes differences in event prevalence across industries and relationships between event factors: private placements and dividends…
This Chinese-language article describes a customizable stock-selection strategy built around five rules, mainly seeking shares that appear oversold and stable, with some rules intended to identify possible rallies. It distinguishes rule-based coding from an…
This A-share stock-selection approach combines an earnings-surprise proxy with the price response to earnings news. Instead of comparing reported profit with a numerical consensus estimate, it analyzes analyst research-report titles for wording that signals…
The article describes a long-only Chinese equity strategy that uses a ResNet101 image classifier to identify strong stocks during pullbacks in an established uptrend. Its rationale combines buying a retracement in a strong trend, favoring stocks that…
This research summary links debt-cycle phases across government, financial, and household sectors to movements in bonds, equities, and commodities in China. It describes a transmission mechanism: rising leverage and easier credit may support bond prices,…
This brief platform discussion answers how to access factor values from code in a BigQuant backtest. Its suggested workflow is to read the data frame attached to the backtest context’s data options during the initialization function, making the factor data…
This tutorial introduces feedforward neural networks, convolutional neural networks, recurrent neural networks, and LSTMs. It explains how perceptrons combine features with learned weights and an activation function, how layers build representations, and how…
The study estimates duration for medium- and long-term pure bond funds using rolling regressions of fund returns on bond-index returns across maturity segments. It compares constrained linear regression, stepwise selection, and LASSO, selecting LASSO to…
The response explains how to reference the current close alongside earlier close values in a BigQuant factor expression. It constructs a series of conditional comparisons: for each of several prior indexed closes, it checks whether the current close is lower…
This report examines the small-cap premium in China’s A-share market and a model for timing shifts between small- and large-cap stocks. It measures the premium through small-cap stocks’ monthly excess return over large caps, and reports that the historical…
The article explains Bollinger Bands as a moving average surrounded by upper and lower bands set two standard deviations away. It also introduces band width as a way to identify volatility contraction, or a squeeze, which may precede a breakout but does not…
The report combines cross-sectional equity factors with a set of three macro cycle indicators in a random forest model. The cycle features act as market state signals, allowing the model to apply different stock-selection logic across conditions. The authors…
This research summary presents a framework for replicating the returns of an index, fund, or individual stock with a selected set of holdings. It first applies LASSO regression to choose securities that capture the target portfolio’s characteristics, then…
The article proposes a recovery approach for a losing equity position that avoids adding shares while price is still falling. It advises waiting for a low-price consolidation and a volume increase as signs that selling pressure may have eased, then using…
The document introduces Smart Beta as index investing that uses rules other than market-cap weighting to increase exposure to selected risk factors. It presents the approach as a middle ground between active and passive investing, with the potential to build…
This guide describes participation in a Chinese A-share quantitative challenge with factor discovery and end-to-end modeling tracks. Both target future 30-minute VWAP returns using minute bars and order book snapshots. For the factor track, submissions…
This study note explains how to build a directed stock network from news coverage: a stock named in a headline is treated as a lead, while stocks mentioned in the article body are followers. Edge weights count their co-occurrences over a rolling window. The…
This brief troubleshooting exchange addresses why two backtests can report different returns even when their factors and backtest dates match. The response attributes the mismatch primarily to a difference in training-set data volume. It adds that using the…
This brief forum exchange addresses a feature calculation that displayed missing values and offers a warning relevant to strategy construction: using a shift with a negative offset can incorporate future observations into a feature. Such a feature may appear…
The note distinguishes selecting a stock universe from testing whether a factor can rank future returns within that universe. It describes factor analysis as sorting stocks by a factor, dividing them into equal-sized groups, and comparing group returns.…
This platform support discussion explains two apparent backtest anomalies in a single-stock strategy: why a position did not begin on the requested date at full allocation, and why the stock appeared to be sold later. The response attributes the delayed…