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.
347 documents
The document summarizes research on forecasting multiple future steps from limit order book data. Rather than predicting only one future point, the proposed approach uses sequence-to-sequence encoder-decoder networks with attention to generate a path of…
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 short forum exchange explains how to configure BigQuant’s trading engine to rebalance on a weekly or monthly schedule. For weekly scheduling, it specifies the weekly trading-day mode and a day value of 5; for monthly scheduling, it specifies the monthly…
This forum post describes an AttributeError in a BigQuant high-frequency backtest. The copied trade-module code treats each key in the portfolio positions mapping as an object with a symbol attribute. In the HFTrade interface, the key is already a string…
This project explores combining strategies associated with different market styles. The author says market styles can persist over a period, so a strategy that fits a clearly expressed style may adapt better to prevailing conditions. They changed a provided…
This article surveys six implementation choices that shape equity factor strategies: selecting proxy measures, constructing portfolios, combining factors, allocating among them, trading, and managing risk. It argues that one factor can be represented by…
This Chinese-language event listing outlines a dynamic trading approach for timing exchange-traded funds. It identifies three components: selecting a pool of highly liquid ETFs, ranking candidates with multiple momentum dimensions, and adjusting the approach…
This submission outlines an intraday stock-selection idea for a day when a market theme is breaking out. It proposes identifying a popular sector early, using large orders that hold at the daily price limit as a sign of a clear direction, then ranking…
This older Chinese-equity strategy looks for stocks that rally to the daily limit, pull back, and later break to a new high. It defines a pullback as any post-limit-up close below the earlier limit-up price. After the pullback, a new high triggers a purchase…
This BigQuant example shows how a China stock universe selector can be connected to a trading engine that reads a daily signal table. The engine filters rows to the current date, closes existing positions once the elapsed time since their last sale reaches…
The document outlines a rule-based strategy for the Tianhong ChiNext ETF, using recent closing prices to create a reference price and comparing the current price and volume with that reference. It describes buying after a large decline and selling after a…
This retrospective contrasts rule-based stock selection with machine-learning ranking and describes backtesting as a way to evaluate a strategy on historical market data. Its central caution is that a strong fit on a small sample can reflect an irrelevant…
This brief troubleshooting exchange addresses a KeyError in a trading strategy. The suggested first step is to inspect the value represented by the variable `s`, since the exception may arise when that value is used to look up a position that is not present…
This forum question concerns modifying a portfolio sell routine so that, when the stock allocation exceeds 60% of total portfolio value, the excess exposure is reduced by selling holdings from the bottom of a ranking. The supplied code builds a set of…
The article discusses data integration challenges when developing strategies across US equities and forex. It highlights differences in update speed, price conventions, and data formats, arguing that timestamp misalignment and latency can create gaps between…
This discussion explains a mismatch in which a simulated trading run produces no signal even though a backtest does. The reported cause is a SQL query using a one-row lead on closing prices. At date t, that field requires the closing price from t+1, which is…
This short forum post asks whether a linear equity strategy can compare a stock’s ranking when purchased with its current ranking and sell after sufficient deterioration. The example uses a small-capitalization strategy holding ten stocks: a stock bought at…
A brief forum exchange addresses a user whose stock strategy appears not to run. The response suggests two checks: use English names for features, and print the daily buy and sell candidate lists to see whether any stocks meet the strategy’s conditions. The…
This Chinese-language post discusses connecting BigQuant research with Guojin Securities’ QMT platform for automated live trading. Its concrete example is a stock strategy that first processes daily data to select a watchlist, then monitors those names and…
A BigQuant user raises a timing problem involving premarket data processing in backtests. In the example, a signal generated on one day leads to an order for the next day; premarket history in the backtest appears to expose that day’s open and close. Such…
This article contrasts retail investors' execution environment with that of quantitative firms. It describes exchange co-location and direct connectivity as ways to reduce signal and order latency, then discusses how automated systems may react quickly to…
The article discusses two reported measures intended to reduce speed advantages for quantitative firms in China’s A-share market: removing servers located inside exchange facilities and adding latency equivalent to a stated 200-kilometer separation. It…
The article examines China’s A-share T+1 rule, which generally prevents investors from selling shares on the same day they buy them. It presents four arguments in the debate: the rule may curb impulsive retail trading, constrain some forms of repeated…