Qlib
github.comOrganize machine-learning experiments for quantitative investment research
Organize machine-learning experiments for quantitative investment research
Research investments and discuss your plans with an investment coach
See how an asset allocation behaved across different starting years
Backtest portfolio allocations with cash flows, benchmarks and simulations
Search public trading disclosures and compare the dates behind them
Compare strategy experiments across assets, parameters and historical periods
Query and deliver institutional pricing and reference data
Explore markets and portfolio tools in live or virtual mode
Save chart configurations and organize repeatable market scans
Build stock scans and inspect trading layouts in a paper account
Reconcile dividend expectations with portfolio transactions and payments
Track investments and examine account and portfolio performance
Connect financial data providers to Python and research applications
Compare Canadian funds and model portfolio allocations
Examine stock-factor returns, predictive relationships and turnover
Build trading tools and examine cBot behaviour on historical data
Compare company fundamentals visually with historical stock valuations
Host coded or visual strategies through shared broker connections
Turn portfolio returns into charts and risk-analysis summaries
Research international banking, liquidity and financial-market statistics
Research and backtest quantitative strategies in notebooks and code
Create reusable chart conditions and filter stock watchlists
Explore international macroeconomic datasets and projection vintages
Calculate portfolio returns from a complete transaction history