Knowledge library

This configuration defines an equity prediction workflow for China’s CSI 300 universe. It applies robust feature normalization and missing-value filling, drops labels with missing values, and ranks labels cross-sectionally. An ordinary least squares linear…

This notebook demonstrates an end-to-end Qlib workflow for a China-market stock ranking model. It initializes Qlib data, uses the CSI 300 universe and Alpha158 features, and trains a LightGBM model on historical data with separate training, validation, and…

DoubleEnsemble is an ensemble framework for financial prediction that addresses noisy training data and large feature sets. It combines two procedures: it uses each sample’s learning trajectory during training to identify influential examples and adjust…

This overview introduces reinforcement learning as a way to learn sequential decisions by interacting with an environment and maximizing accumulated reward. It outlines the agent, environment, policy, and reward, and explains how delayed feedback differs…

This Qlib documentation describes a workflow for generating, storing, training, and collecting multiple research tasks. A task can include a model, dataset, and recorded outputs. Task generators such as RollingGen can create tasks for different date…

This Qlib documentation explains why historical strategies need the versions of financial data that were available at each past decision time. Financial statements can be revised after publication; using only the latest value in a historical simulation can…

This document describes a data preparation workflow for daily risk estimates on China A-shares. For each date, it selects the CSI 300 constituents, gathers a rolling window of closing prices, calculates returns, and clips extreme returns at the…

This document presents a framework for testing trading decisions made at multiple time scales together. It argues that portfolio selection and intraday order execution should interact within one backtest because execution quality can change which…

This configuration specifies a Qlib workflow for a TabNet model using the Alpha360 feature handler and CSI 300 instruments, with the index as benchmark. It sets a two-day-ahead close-price return label, applies robust normalization and missing-value filling…

This workflow note explains how to prepare data when training models across rolling windows. As each window advances, the training sample changes, and learned processor state—such as means and standard deviations—must be recalculated for that window. Reusing…

This configuration specifies a Qlib workflow for training a CatBoost model on Alpha158 features for the CSI 500 universe. The data spans 2008 through mid-2020, with training through 2014, validation during 2015–2016, and testing from 2017 onward. The model…

This configuration describes a Qlib workflow for training a Localformer model on China A-share data and evaluating its predictions as a portfolio signal. It uses the CSI 300 universe and benchmark, an Alpha360 data handler, robust feature normalization,…

This configuration defines a Qlib workflow for ranking CSI 500 equities with a LightGBM model and Alpha360 features. It uses cross-sectional rank normalization for labels and trains on data from 2008 through 2014, validates on 2015–2016, and evaluates a…

This Qlib configuration defines a Chinese equity research workflow using the CSI 300 universe and Alpha158 features. It trains a double ensemble of gradient-boosted models, with both sample reweighting and feature selection enabled, then evaluates signals…

This example shows a two-stage workflow for keeping predictions current with Qlib’s online model tools. First, it trains a model using a CSI 300 gradient-boosting task configuration and marks the resulting model as the online model. Second, it calls the…

This Qlib configuration trains an ADD model using a GRU base model and Alpha360 features to rank CSI 300 stocks. Features are robustly normalized and missing values are filled; labels are cross-sectionally rank-normalized after missing labels are dropped.…

This configuration specifies a Qlib research workflow for China A-share stocks in the CSI 300 universe. It uses Alpha360 features, robust feature normalization and missing-value filling, and cross-sectional rank normalization for labels. The prediction…

This configuration describes a Qlib experiment for CSI 300 equities using a LightGBM regression model. The dataset combines daily features with intraday one-minute data resampled to a daily frequency through a custom handler. The configured label frequency…

The document defines Qlib data handlers for one-minute bars, aimed at high-frequency research and backtesting. The training handler creates normalized open, high, low, close, and approximate VWAP features, along with volume features. Price features are…

This configuration describes an order-execution backtest using five-minute market data and an order file. The main strategy uses a recurrent network with a PPO policy, a categorical action interpreter, and a state interpreter that supplies recent intraday…

This configuration describes a Qlib workflow for training a TCTS model on the CSI 300 universe using Alpha360 features. The data span 2008 to 2020, with training through 2014, validation over 2015–2016, and testing from 2017 to mid-2020. Feature processing…

The document introduces Qlib’s online-serving components for applying trained models to current market data. It describes a workflow that can produce predictions in live conditions and support real trading based on those predictions. The named components are…

This document presents an optimization-based alternative to a simple top-ranked stock strategy. It describes using Qlib’s EnhancedIndexingStrategy to seek a balance between portfolio return and tracking error against a benchmark, with correlation and…

This configuration specifies a reinforcement learning setup for order execution using Proximal Policy Optimization. It defines a categorical action interpreter, a recurrent network, and a full-history state representation built from intraday and prior-day…