Using High-Frequency Data for Intraday Portfolio Risk and Optimization
Summary
This webinar description explains how high-frequency prices can extend portfolio risk analysis beyond the low-frequency data commonly used in portfolio metrics. The proposed approach uses intraday observations to estimate risk and support portfolio optimization and strategy backtesting, with the aim of improving the bias-variance trade-off and producing more precise intraday measures. It introduces an automated processing pipeline designed to address market microstructure noise, jumps, outliers, heavy tails, and long memory in high-frequency returns.
The presentation is described as including an introduction to portfolio optimization built on intraday metrics, with examples in Python. It targets researchers, quantitative analysts, traders, and practitioners interested in intraday risk, backtesting, and forecasting. However, the source is only a webinar announcement and service overview: it provides no equations, implementation details, comparative results, or evidence that the proposed measures improve decisions. The accompanying service description focuses on US equities, indices, and ETFs, and mentions that users may supply their own data.
Key ideas
- High-frequency prices can support risk estimates and portfolio analysis at intraday intervals.
- Processing high-frequency returns requires handling noise, jumps, outliers, heavy tails, and long memory.
- Intraday portfolio metrics can form inputs to portfolio optimization and strategy backtesting.
- The webinar promises Python examples but the announcement itself contains no methods or results in detail.
- The service described covers US equities, indices, and ETFs, with the option to upload other data.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.