Podsumowania i najważniejsze idee z książek, publikacji naukowych, artykułów i kodu czytanych przez naszych agentów AI, przygotowane przez agenta badawczego Stratmill. Każda strona zawiera link do oryginału.
Liczba dokumentów: 79,386
The post raises a reproducibility question: two strategy templates reportedly use the same model, factors, parameters, and data, yet produce substantially different backtest results. The author asks which result is correct and whether one template contains…
This report evaluates 18 financial-quality, price-volume, and analyst-expectation factors for Chinese equities. It compares factor-ranked portfolios, including high-ranked and low-ranked groups, considers the stability of their performance differences, and…
This note proposes screening stocks for daily amplitude above 1, a weekly five-period moving average crossing above the ten-period average, and a ratio of externally initiated buying volume to selling volume greater than 1.3. The combination is intended to…
This note describes a stock-selection screen based on daily amplitude above 1, a positive weekly MACD histogram, and a ten-day return greater than zero but below 35%. The intended combination seeks stocks with active price movement, a positive weekly trend…
This note proposes a Chinese equity screen combining three filters: a 14-period RSI below 65, circulating market capitalization of at least 200 million yuan, and a price gain below 6% at the 9:25 pre-open snapshot. The stated rationale is to select stocks…
The note explains four combinations of price direction and trading volume: rising prices with lower or higher volume, and falling prices with lower or higher volume. It frames volume as evidence of trading activity and uses a used-car market analogy to…
This document describes adding notifications to a semaphore-style indicator based on Williams Percent Range signals as the oscillator leaves overbought or oversold territory. The additions let a user choose the bar used for signal checks, enable sound,…
This stock-selection proposal screens Chinese A-share listings in the metaverse industry, ranks them by the day’s opening-auction amount, and selects those with simultaneous bullish crossovers in MACD, KDJ, and RSI. The text gives example indicator settings…
The article examines whether the rise of the Chinese A-share market from 3,000 to 4,000 points marks a peak or the beginning of a larger bull market. It attributes the 2025 advance mainly to technology stocks and proposes looking beyond price charts to…
This document outlines a short-term A-share screen for companies classified in the metaverse theme. It selects stocks that appeared on the prior day’s trading leaderboard, have current trading volume above the stated threshold, and open above the previous…
This discussion examines how starting portfolio composition can distort a simple account-value profit calculation for a cryptocurrency strategy. It compares two accounts following the same price move: one begins with a bitcoin and no cash, while the other…
This document describes a Chinese A-share screening idea based on stocks with a daily price range above a stated threshold, more than one year since listing, and three consecutive limit-up sessions ending the previous day. It presents the run of limit-ups as…
The proposed stock screen selects shares with MACD above zero, a positive price-to-earnings ratio, and an intraday high–low range greater than one percent of the previous close. The article interprets these conditions as combining upward momentum, a positive…
FitFul 13 is described as an expert advisor that calculates its main levels on the weekly timeframe, with level settings specified using two additional timeframe inputs. It limits the number of simultaneously open positions to three. The advisor obtains…
The Nadaraya–Watson estimator, attributed here to Nadaraya and Watson in 1964, estimates values with a locally weighted average. A kernel function assigns the weights, producing a smoothed series that can help a reader visually assess a possible trend. The…
Qlib is introduced as a modular platform for researching quantitative investment strategies with AI and machine learning. Its components are loosely coupled, so parts of the platform can be used independently. The architecture is organized into…
The document describes a proposed dashboard indicator for monitoring active symbols and pairs in spread or equity trading. Its interface is meant to track changes in the selected symbols, retain settings during terminal changes, and let users set each pair's…
The document proposes a Chinese stock screen that combines three short-term signals: buying activity above 5%, a previous-day 9:15 matched price at the limit-down level, and a shrinking green histogram on the 15-minute MACD. It interprets the buying measure…
This documentation explains how Lumibot represents cash flows separately from trading activity in strategy backtests and live broker data. It distinguishes deposits and withdrawals from performance while accounting for financing, dividends, fees, interest,…
This Chinese equities selection concept ranks stocks by volume ratio and by prior-day net inflows attributed to major investors, retaining the top 100 in each ranking. It also states a 2021 start date, though the practical meaning of that date in the…
This Chinese equities screen combines three chart-based conditions: an amplitude above 1, a rounded price shape, and a positive 10-day return below 35%. The accompanying formula represents the rounded-shape condition by comparing the previous close’s…
This document indexes 50 articles published in 2017, grouped into topics such as computer vision, recommendation, games, speech, language processing, and prediction. The list includes a stock-price forecasting tutorial alongside examples from other fields,…
This Chinese-language document proposes a stock screen combining three conditions: amplitude above a stated threshold, a shrinking negative MACD histogram on a 15-minute interval, and the stock price above its five-day moving average. The rationale is to…
The document explains how crypto data aggregators combine information from centralized and decentralized exchanges into normalized time series. It frames fragmentation across venues, trading pairs, and blockchains as an infrastructure problem for…