Gautam Mitra, CEO, Optirisk/UNICOM

Robin Wigglesworth, Global finance correspondent, Financial Times

Volatility is an inevitable part of financial markets. But over the past six decades, volatility has come to dominate risk-management models across the finance industry. At the same time, a motley crew of academics and investment bankers have turned volatility itself into something that can be sliced and diced, bought and sold, just like any bond, stock or barrel of oil. This has arguably made the global financial system more fragile in the process. Here is the story of how volatility became a virus that infected the entire finance industry.

Devesh Shah, Retired Partner, Goldman Sachs & Co and Co-Inventor of the VIX Volatility Index

The VIX Volatility Index is a powerful idea and an index for measuring uncertainty in the equity market. What makes it even more powerful is the ability to almost capture it in your fist through tradable derivatives on the VIX itself. Many cross-sectional, inter-market concepts were necessary in the creation of the VIX Index. Several people, each with unique perspectives came together. Let us dive a little deeper into the formation of one of the most popular and successful listed derivatives products of the last twenty years.

PROF GAUTAM MITRA, CEO, OptiRisk Systems/Visiting Professor, UCL

TBC

Raul Glavan, Consultant Artificial Intelligence & Asset Management | Trader | Speaker | UBI Enthusiast

TBC

Dr. Ernie Chan, Founder, Predictnow.ai Inc

One major impediment to widespread adoption of machine learning (ML) in investment management is their black-box nature: how would you explain to an investor why the machine makes a certain prediction? If you don’t understand the underlying mechanisms of a predictive model, you may not trust its predictions. Feature importance ranking goes a long way towards providing better interpretability to ML models, and feature selection improves out-of-sample performance of ML models.

Euan Sinclair, Quantitative Analyst, Hull Tactical

• Review of SKEW
• Extracting skewness for risk reversals
• The skewness premium
• Monetizing skew pemium

DR. Francesco Cricchio, CEO, Brain

Brain is a research oriented company that develops proprietary signals and algorithms for investment strategies on financial markets, combining Statistical methods, Machine Learning and Natural Language Processing techniques.

We will show the application of Brain Artificial Intelligence Platform to create proprietary datasets that are integrated by Clients in systematic trading strategies, some datasets at ticker level like the Brain Sentiment Indicator, Brain Machine Learning Stock Ranking and Brain Language Metrics on Company Filings; other datasets are at general market level, like the Brain Market Sentiment, and Risk ON/ OFF signals. We will focus on the latest released dataset Brain Language Metrics on Company Filings and the related use cases exploring the language analysis of company reports and the study of possible relations with firms’ future performance as discussed in recent papers.

Finally we will show the application of the NLP module of the platform to perform a thematic selection, among a large universe of companies, of a basket of stocks whose business is focused on a specific theme (e.g. nanotechnology, cell therapy, genetic engineering and others). The selection can be combined with proprietary alternative datasets and allows to create at low management fee Thematic or Smart Indices, active and passive ETFs, mutual funds.