Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
3,481 dokumenttia
The article answers practical questions about machine-learning stock strategies. It says the platform separates training and test periods by time, with the test interval serving as the backtest, and describes a setup without a separate validation set. It…
This research note reviews the CSI Dividend Index and the Bosera CSI Dividend ETF, which tracks it. The index draws 100 Shanghai and Shenzhen A-shares from stocks with high average after-tax cash dividend yields over the prior two years, then weights them by…
This monitoring framework tracks valuation measures and fund holdings across major Chinese equity indexes, industry groups, and selected large companies. It covers price-to-earnings, growth-adjusted valuation, price-to-book, dividend yields, and fund…
This research note studies value-based stock selection in Hong Kong equities, using the Hang Seng Composite as its universe. Because Hong Kong main-board companies are not required to publish quarterly reports and may change their fiscal year-end, the…
The discussion asks how to detect whether a value, such as a closing price or trading volume, has risen or fallen continuously over a chosen number of days. It points to a pair of time-series functions: one counts consecutive rises, and a corresponding…
The discussion explains how to interpret a Chinese stock daily-bar dataset that stores fully back-adjusted prices. It says the dataset includes a back-adjustment factor and describes recovering the underlying market price by dividing the adjusted close by…
This report summary examines Chinese public mutual funds around the second quarter of 2018, focusing on actively managed equity funds. It describes falling scale and share counts for active equity products, differences in reported returns across fund types,…
This report summary examines Chinese public mutual funds around the second quarter of 2018, focusing on actively managed equity funds. It describes falling scale and share counts for active equity products, differences in reported returns across fund types,…
The document presents eight discretionary rules for interpreting stock price action. It treats steady small advances as possible accumulation and repeated sharp gains as a potential overextension. It also compares each stock’s behavior with the broad market:…
The document groups common Chinese A-share factors into style, technical, and fundamental categories. Style factors include market, size, and value; technical factors include reversal, low turnover, and low volatility; fundamental factors cover profitability…
The document introduces the Commodity Channel Index (CCI), a technical indicator calculated from high, low, and close prices. It first derives typical price as the average of those three values, then compares typical price with its moving average and scales…
The document explains a Brinson-style framework for decomposing portfolio returns into a benchmark baseline, the combined effects of active asset allocation and the benchmark, the combined effects of security selection and the benchmark, and the actual…
This project outlines a mean-reversion pairs strategy for Chinese futures. It screens candidate contract pairs for cointegration with an Augmented Dickey-Fuller test, estimates a changing hedge ratio with a Kalman filter, and measures spread behavior with…
This short description presents TEMACandle, an indicator that displays a price series as candlesticks after processing it with the Triple Exponential Moving Average (TEMA) algorithm. The transformation applies TEMA smoothing to the underlying price data and…
This research summary describes a multi-factor investment workflow that combines alpha forecasts, a risk model, transaction-cost estimates, portfolio optimization, and performance attribution. It argues that simple score-based selection or sector and…
This brief Chinese-language support note explains a prediction-data problem traced to missing values in a rolling price-range factor. The example factor compares a short moving average of the high-low range with a longer moving average. According to the…
The report asks whether exposure to macroeconomic policy uncertainty is priced in Chinese A-shares. It describes a news-based economic policy uncertainty index and estimates each stock’s EPU beta through time-series regression. Stocks are sorted into five…
This study examines whether price-to-earnings ratios, cyclically adjusted P/E (CAPE), and the bond-stock earnings yield measure (BSEYD) can signal major downturns in the Shanghai and Shenzhen composite indexes. It also describes return features in the two…
This troubleshooting note describes a SQL binder error that occurs when a normalization function is used in a query joining two stock-factor tables. Both tables contain a date column, so passing an unqualified date reference to the function leaves the…
This discussion examines why published quantitative findings and attractive backtests may fail to reproduce or translate into tradable returns. It explains how publication incentives, selective reporting, repeated testing, flexible data choices, and…
The document explains how to construct factors grouped by Chinese stock market concepts when a built-in grouping expression does not recognize the concept field. For standard industry groupings, it gives a group-mean example using a level-two industry…
The document describes a problem encountered when using an initialization module to set a day counter and prevent duplicate daily trades. In backtests, the counter reportedly advanced across several days, but in simulated trading the same first-day trade ran…
This short forum post asks how to add market-timing conditions to a strategy backtest. The author has seen strategies reduce or alter exposure after several consecutive market declines and is interested in alternatives based on whether the Shanghai Composite…
This brief introductory response defines quantitative investing as finding patterns in historical data, translating them into a model and strategy, and using software to execute trades according to the resulting rules. It highlights discipline as a benefit:…