Main Conference Day 2:
Friday 19th May
09.00 – 09.45: Learning Market Data Anomalies
- Why anomaly data detection is crucial for market risk management
- Techniques: from simple statistics to isolation forest and (variational) autoencoders
- Comparing and reporting outputs
- Operational framework
Abstract
Everyday market risk managers are required to check a huge amount of market data, scenarios and positions used to compute market risk measures. Some data may present anomalous values because of a wide range of reasons, e.g. bugs in the related production processes, sudden and severe market movements, etc. Hence, it is crucial to integrate the daily data quality process with automatic and statistically robust tools able to smartly analyse all the available information and identify possible anomalies (the “needles in the haystack”). To this purpose we combined both simple statistics and machine learning algorithms to build an anomaly detection framework which is general enough to cover different asset classes and data dimensionalities (multiple curves, surfaces and cubes). The results are encouraging but they strongly depend on assumptions and parameters, keeping crucial the human supervision.
Marco Bianchetti:
Head of Internal Model Market Risk, Intesa Sanpaolo
Manola Santilli:
Market Risk Analyst, Intesa Sanpaolo
Marco Scaringi:
Quantitative Analyst, Risk Management, Intesa Sanpaolo
09.45 – 10.30: Forecasting Inflation with Machine Learning, alt data and Python
Inflation has become a key topic in recent months. In our talk, we discuss how to approach the topic from a machine learning perspective, and how to incorporate alternative data in the process. We will also discuss the tech stack we have used and the various Python libraries involved, as well as how we’ve speeded up the code.
Saeed Amen
11.00 – 11.45: Validating Synthetic Data with AI
We discuss the application of calibration methods from Generative Adversarial Neural Nets to the computation of distributional metrics for data samples and in doing so, point the way to the measurement of synthetic data quality.
Jodie Humphreys:
Director, Bank of America
11.45 – 12.30: Sentiment Investing, with Applications for Alpha and Risk Modelling
Ganchi Zhang:
QIS research, Director, Deutsche Bank
Gianpaolo Tomasi:
QIS research, Director, Deutsche Bank
13.30 – 14.15: Arbitrage-free FX implied volatility by variational inference
We Introduce an approach to obtain no-arbitrage FX implied volatilities from bid and ask of ATM, risk reversal, and butterfly volatilities
- Market convention in FX option market
- Variational inference and Kullback-Leibler divergence
- Conditions for arbitrage-free and correct order in strike rates
- Algorithm
- Numerical examples
Yoshihiro Tawada:
Director: Head of FX-flow Quant Modelling, MUFG Securities EMEA plc
14.15 – 15.00: Robust Log-normal Stochastic Volatility for Interest Rate Dynamics
Abstract: We present a log-normal SV model for the dynamics of interest rates based on single-factor Cheyette model. We assume non-zero correlation between the dynamics of the model state variable and the log-normal SV driver for modelling implied volatility skews observed in fixed-income markets. We show that the proposed model is consistent with historical evolution of rates and implied volatilities. We present a closed-form solution for swaptions valuation and show that our model is able to fit accurately observed market implied volatilities.
This talk is based on joint work with Artur Sepp.
Parviz Rakhmonov:
Vice President, Quantitative Analyst, Citibank
15.15 – 16.00 What the Pandemic, war in Ukraine and the return of inflation tell you – a contrarian look at ESG
- Geophysical basis of climate and adverse weather events: what do reinsurers think?
- The energy mix and other resource intensive industries.
- Two years after “Peak ESG”, what remains? ESG versus free markets.
- Is the financial industry the right tool to craft environmental policy?
- How to invest your portfolio through a greenwash boom and bust?
Erik Vynckier:
Interim Chief Executive, Foresters Friendly Society
09.00 – 09.45: Leveraging Large Language Models to extract ESG information in practice
Robert Dargavel Smith:
Lead Data Scientist, Clarity AI
09.45 – 10.30: Slow vs fast ESG scores: do they measure the same thing?
- What are the similarities and differences between “slow” ESG scores (of Sustainalytics, Moody’s and such) and “fast”, media-based ESG data, obtained with AI and NLP?
- What can we learn from this comparison?
- What are financial consequences of using fast ESG information?
- Can fast ESG data help us design successful trading and investment strategies?
Svetlana Borovkova:
Head of Quantitative Modelling, Probability & Partners. Associate Prof, Vrije Universiteit Amsterdam
11.00 – 11.45: Fundamental ratios as predictors of ESG scores: a machine learning approach
Rita Laura D’Ecclesia:
Professor of Quantitative Finance. Sapienza University of Rome, Italy
11.45 – 12.30: CO2eVA: Pricing Carbon Externalities Transition
Chris Kenyon:
Director: Head of XVA Quant Modelling, MUFG Securities EMEA plc
13.30 – 14.15: Carbon-Equivalence Principle in Action
- Carbon-equivalence principle
- Policy-impacted climate finance
- Marginal financial net-zero
- Minimization of carbon costs
- Green hedge business
Andrea Macrina:
Professor of Mathematics, University College London (UCL)
15.15 – 16.00 What the Pandemic, war in Ukraine and the return of inflation tell you – a contrarian look at ESG
- Geophysical basis of climate and adverse weather events: what do reinsurers think?
- The energy mix and other resource intensive industries.
- Two years after “Peak ESG”, what remains? ESG versus free markets.
- Is the financial industry the right tool to craft environmental policy?
- How to invest your portfolio through a greenwash boom and bust?
Erik Vynckier:
Interim Chief Executive, Foresters Friendly Society
Download Event PDF