Automated Trading Insights for Finance Using Machine Learning & Alternative Data
Machine Learning (ML) and Predictive Analytics are now embedded in a broad variety of use cases in Quantitative Finance, from information extraction to sentiment analysis, from factor scoring models to complex instrument pricing methods, and from risk premium mining to portfolio construction models.
Quant traders and data scientists require automated ML & AI technologies to quickly extract actionable information from unstructured and increasingly non-traditional sources of data. We will illustrate the use of such derived signals in constructing promising trading strategies through novel use cases.
Outline/Structure of the Talk
This talk will provide a brief overview of the following topics:
- The broad application of machine learning in finance: opportunities and challenges.
- Construction of scoring models and factors from complex data sets, including: News/Social Media, Supply Chain Network, Options Prices and ESG (Environmental, Social & Governance).
- Use of alternative data, such as extreme weather (i.e., cyclones, snowfall) to quantify the weather's impact on companies that own retail stores and factories.
- Machine Learning techniques for asset pricing, replacing complex quant models (i.e., PDE, Monte Carlo) for an efficient pricing of derivative securities.
- Automated News & Data Driven insights – using data science to build triggers that can alert market participants in a timely manner. We will demonstrate event study examples that show the efficacy of such machine generated insights.
use of ML/AI methods for finance and unique challenges in finance (noisy data), implementation in trading strategies
Data Scientists, Quants, Financial technologists
Prerequisites for Attendees
Basic knowledge of ML and Finance