Building Equity Factors with BigQuant's DAI Data Engine
Summary
This guide describes how a BigAlpha competition participant can build equity factors using BigQuant’s DAI data engine. The specified universe is the historical membership of the CSI 1000, and the listed inputs include one-minute bars and order-book snapshots, financial data, instrument listings, existing factors, and risk exposures. Examples show querying and aggregating intraday prices in SQL, applying a user-defined function, and transferring query results among pandas, Polars, and Arrow for further calculation.
The guide also explains how to combine DAI queries with external data frames, handle timestamp-to-date conversions, and use time-series and cross-sectional operators. It notes that compression can reduce memory use for large queries and that instrument type conversions may be needed for compatibility. The factor example is an average-to-last-price ratio, not a tested investment signal. The document explains the competition’s data and computing workflow, but reports no factor performance, validation procedure, or trading results; its examples should be read as implementation patterns rather than evidence of alpha.
Key ideas
- The competition limits factor construction to specified data sources and a historical CSI 1000 universe.
- The available inputs include minute bars, order-book snapshots, financial data, factor data, and risk exposures.
- DAI examples demonstrate SQL aggregation and custom functions for calculating factors.
- Query results can be moved between DAI and dataframe or Arrow formats for additional processing.
- Date casting, operator grouping, compression, and instrument data types affect correct and efficient calculations.
- The sample factor illustrates computation only and provides no evidence of investment performance.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.