FinLab Docs

Turn an investing idea into a tested strategy in a few lines of Python

Load US and Taiwan market data, write stock-selection rules, backtest, and trade daily. Every step comes with code you can run.

pip install finlab

Quickstart Install, load data, write a condition and run your first backtest in five minutes. No code needed Describe an idea in Studio; AI writes the code and backtests it for you. API reference Every function’s parameters, returns and examples, generated from the source.

How FinLab works

Every dataset is a table of dates by stocks. A condition works on the whole table at once; each True is a stock to hold. Hand it to sim() to backtest, then schedule it to run daily.

1 Get data
data.get('price:adj_close')
Dates down, stocks across
2 Write a condition
close > close.average(60)
True = hold that day
3 Backtest
sim(position, resample='M')
Returns, drawdown, trades
4 Go live
PortfolioSyncManager
- BuyAAPL
- BuyMSFT
- SellNVDA
Updates and orders every day

	AAPL	MSFT	NVDA
10/27	385.93	610.66	223.87
10/28	382.29	610.30	221.24
10/29	387.94	609.30	219.47

	AAPL	MSFT	NVDA
10/27	True	False	True
10/28	True	False	True
10/29	True	True	False

Walk through it in the quickstart

Guides by task

Download dataPrices, fundamentals, flows in one line Write conditionsRank, combine, hold until exit BacktestReturns, drawdowns, trades Place ordersConnect a broker and send orders Run dailySchedule runs and rebalance alerts Factor analysisIC, quantile returns, crowding Machine learningFeatures, labels, models, backtests OptimizeCompare many condition sets

Strategy examples

See all

Need help?

FAQ Glossary Changelog Ask support