This website uses cookies to provide a better user experience. Please find more information Okhere. #CCCCCC #000000

SEMINAR

11/12 Nov 2019 in Prague

Deep Learning–Applications in Market Risk and Economic Capital Modelling: Deep dive

Deep learning techniques represent a certain part of wider machine learning methods and have become increasingly popular for a variety of real-life applications solving complex high-dimensional problems.

So far, typical applications for deep learning architectures such as deep neural networks and recurrent neural networks include speech and pattern recognition, language processing, audio recognition or machine translation. In all these applications, deep learning techniques were able to yield break-through results due to their highly flexible and innovative architectures and their approach of training models towards a set of given data.

Hence, given the variety and complexity of problems in the insurance industry combined with the typically large amounts of available data, practitioners have started applying these techniques in the insurance industry.

This seminar will exclusively focus on applying deep learning techniques for market risk modelling and the wider economic capital modelling space as well as asset allocation and actuarial business planning which represent areas of great importance for insurance companies where deep learning techniques have typically not been widely used before. Main goal of the seminar is to present relevant tools and techniques from deep learning and bring them together with applications in market risk, economic capital modelling, asset allocation and actuarial business planning. Examples are proxy modelling, projecting cash flows and economic balance sheet items (incl. the Solvency II ratio) in the future and prediction of economic time series.

The seminar will be highly practical; all major applications presented in the seminar will be followed by hands-on sessions where the participants will be able to implement the techniques under supervision and apply them to data sets.

Additionally, EAA offers the webinar „Deep Learning – Applications in Market Risk and Economic Capital Modelling: Overview on current state-of-the-art techniques” on 25 September 2019 | 10:00 - 12:00 CEST. The speakers describe the difference between the webinar and the seminar as follows:

The webinar provides an overview on current state-of-the-art techniques and illustrates them based on two case studies, while the seminar offers a deep dive into these techniques providing more and additional technical and theoretical background and allows the participants to apply DL techniques themselves under the guidance of the speakers.

Participants of the webinar who also take part in the seminar in Prague will get a discount of € 50.00 on the seminar fee.

Organised by the EAA – European Actuarial Academy GmbH.

 

Participants

The practical sessions will make use of Keras, Tensorflow and R. Guidelines on how to install these tools on your own laptop will be provided several weeks prior to the beginning of the seminar. Technical support regarding the installation will be provided during the seminar, if necessary.

No special prior knowledge is required.

Purpose and Nature

The main purpose of the seminar is for the participants to learn which applications deep learning techniques offer in the context of market risk, economic capital modelling, asset allocation and actuarial business planning. Therefore, we will provide an introduction into the wider deep learning framework and then focus on key techniques, tools and ingredients which are particularly useful for the context of market risk and economic capital modelling as well as asset allocation and actuarial business planning. Participants will also learn about the requirements for the successful application of these techniques and their boundaries. The seminar will be highly practical; all major applications presented in the seminar will be followed by hands-on sessions where the participants will be able to implement the techniques under supervision and apply them to data sets.

Language

The language of the seminar will be English.

Lecturers

Dr. Mario Hoerig, Partner, Oliver Wyman Actuarial
Mario Hoerig is a Partner with Oliver Wyman, co-leading the actuarial services offering in the German speaking markets. Mario focuses on quantitative modelling under Solvency II (economic scenario generators for risk-neutral and real-world purposes, ALM studies, risk factor modelling for Solvency II, risk aggregation, economic capital and capital management) and advises some of the largest insurance companies in Europe on these topics.

Dr. Daniel Hohmann, Senior Manager, Oliver Wyman Actuarial
Daniel Hohmann is a Senior Manager with Oliver Wyman. He has a strong quantitative background and has been advising his clients on a variety of market risk and economic capital topics such as proxy modelling, risk-neutral and real-world scenario generation and time series analysis for market data.

NN
Further speakers from the industry will present and share their experience with deep learning techniques within market risk and economic capital applications.

Participant Feedback

of 5 Points

Venue & Accommodation

The seminar will take place at the

Angelo by Vienna House Prague
Radlická 1g
150 00 Praha 5, Czech Republic
Phone: +420296882707
https://www.viennahouse.com

We have arranged special prices for accommodation. The special rate is 115 € per night in a classic single room including breakfast and VAT. It is valid for bookings by 25 October 2019 out of our allotment “EAA Seminar”. Our allotment includes a limited number of rooms. Kindly book your accommodation directly with the hotel using this booking form, and note the hotel’s cancellation policy.