In-house & Bespoke Training
We draw on the experience of an extensive network of industry and academic experts to deliver courses tailor-made for you.
If you need an entirely new training package designed to your specific needs or a course delivered at a venue of your choice, our expert trainers will come to your organisation and provide bespoke training on topics such as:
- Machine Learning & AI
- Stress Testing
- Interest Rate Modelling
- CVA, KVA & XVA
- Initial Margin Requirements
- Distributed Ledger Technology
- FRTB Fundamental Review of the Trading Book
- MiFID II
- IFRS 9
- Bank Treasury Risk Management & ALM
To enquire about our In-house training services, please contact:
Email : firstname.lastname@example.org
Tel: Neil Clive Fowler, +44 (0) 1273 201352
Machine Learning in Finance
What delegates will require:
Laptops required for all or in groups (we encourage collaboration during the tutorials.) Solutions to problems, including programming assignments, will be provided during the training, so you can follow them. Python is a (de facto) lingua franca of data science and machine learning, so we’ll use it as our primary programming language. We advise that you install the Anaconda Python distribution (64-bit, version 5.0.0, the Python 3.6 variant at the time of writing) by Continuum Analytics. This distribution includes the following libraries, some of which we may use during the training:
- NumPy — the fundamental package for scientific computing with Python; it contains, among other things, a powerful n-dimensional array object;
- SciPy (pronounced “Sigh Pie”)—Python-based ecosystem of open-source software for mathematics, science, and engineering;
- SciKits — SciPy Toolkits;
- Pandas — Python Data Analysis Library;
- StatsModels— Statistics in Python;
- Keras — the Python deep learning library, a high-level neural networks API running on top of TensorFlow, CNTK, or Theano.
There are no formal prerequisites for the course, and we’ll endeavour to explain the foundational concepts during the training if required. However, since data science and machine learning rely on the following disciplines, it is good to brush up on:
- Linear algebra — we are dealing with datasets consisting of many data points and algorithms with many (hyper)parameters; linear algebra is the essential language in this multivariate setting;
- Probability theory — many of the models are versed in the language of probability: for example, disturbances in linear regression models are random variables; frequentist likelihoods and Bayesian priors and posteriors are probabilities; Somewhat less pertinently:
- Information theory — this branch of applied mathematics is concerned with quantifying how much information is present in our inputs; in machine learning we are concerned with extracting as much information as possible;
- Numerical computation — many of the algorithms rely on numerical methods rather than analytical solutions; in practice care is needed to avoid numerical issues such as overflow and underflow, poor conditioning, etc.;
- Optimisation theory — much of machine learning is concerned with optimising (hyper)parameters and therefore utilises the machinery from optimisation theory, such as gradient-based optimisation.
In order to practise machine learning, one needs
- A working knowledge of a convenient programming language, such as Python or R;
- Familiarity with relevant libraries.
- During our trainings, all code demonstrations will be using Python.
- Lecture 1: interpretations of probability— classical, frequentist, Bayesian, axiomatic
- Lecture 2: statistical inference and estimation theory
- Tutorial 1: statistical inference and estimation theory
- Lecture 3: introduction to linear regression: a geometric perspective
- Lecture 4: interpreting the linear regression, multicollinearity
- Tutorial 2: linear regression
- Lecture 5: from statistics to machine learning: bias-variance trade-off, under- and overfitting
- Lecture 6: cross-validation and shrinkage methods
- Tutorial 3: demo of cross-validation and shrinkage methods
- Lecture 7: optimisation, gradient descent
- Lecture 8: neural networks and deep learning
- Tutorial 4: neural networks
Sound Stress Testing and Scenario Analysis
Stress testing has become an important analysis practiced across multiple industries as part of a robust enterprise-wide risk management framework. Since the global financial crisis there has been a greater focus on the regulatory aspects of the implementation and rigorous stress testing program across all major financial institutions. Financial institutions have responded to the crisis and this intensified regulatory scrutiny over the last several years, dramatically increasing their commitment to internal stress testing programs. Throughout this course participants will develop methods to build well structured stress tests and scenario analysis. Exploring and building detailed case studies and realistic stress tests.
1) Methods to build well-structured stress tests and scenario analysis: which technique should we use (Bayesian nets and other methods)?
2) The three main applications:
a. single – transaction analysis
b. asset allocation
c. large and complex portfolios
3) How to root stress testing in solid financial theory
4) How to handle the dimensionality curse (ie, how to cascade a stress view from a small number of risk factors to many asset prices)
5) How to handle the consistency requirement between stress and no-stress risk measures
6) How to associate an approximate probability to the scenario
7) How to carry out sensitivity analysis
8) How to carry out a Monte Carlo simulation for stress analysis
9) Bells and whistles – ie, how to refine the results and extract additional information
Case Studies and Realistic Stress Tests:
During the course the delegates will build a realistic stress-testing scenario chosen by the delegates (Hard Brexit? Italian banking crisis? North Korea crisis?) both for a complex portfolio and for a specific transaction (eg, Hard Brexit and the UK yield-curve steepener trade).
During the construction of the scenario, the insights and techniques learnt during the course will be used in practice. The delegates will go back to their offices knowing how to carry out a realistic scenario themselves.
Rise of the Machines, the Next Frontier of Finance
How you will benefit:
- Gain a profound understanding of what lies ahead of you in the rapidly changing Capital Markets and Capital market structure.
- Understand new technology that is impacting the markets and what FinTech is next to impact the market.
- Explore relevant risk factors that keep market participants up at night. Understand how to diagnose and hedge these risk factors in a volatile market.
- Participants will be better equipped to understand the unique dynamics of the markets. How various factors push and pull, effecting other areas of the market. How regulation, collateral management, and high-frequency trading have an impact on market conditions.
- Participants will address the challenge of today’s market as well as what challenges are on the horizon.
Delegate challenges/Your solutions:
Challenge #1: “I don’t understand what is driving the market?”
Participants will come away from this class understanding not only market structure but the factors that are affecting the market and what to expect in the future in terms of market conditions, future regulation, and other important factors affecting our ecosystem.
Challenge #2: “I don’t understand the new technology such as blockchain or crypto currency.”
After attending our course participants will have a deep and profound understanding of the technology behind the crypto currency’s blockchain, applications, as well as the current dynamics of the crypto currency trading environment. Participants will also learn what to expect in the future for this revolutionary technology
Challenge #3: “I don’t have a clue on what is happening with the future of regulation, & how is Brexit going to impact my life?”
Participants will not only understand market structure conditions but they will also understand market risk conditions that will affect the market going forward. Participants will have a profound understanding of the future of regulation, what it means to them in their business, and what to expect in terms of market conditions because of these changes.
Modern Market structure looking beyond 2020: The rise of alternative technology, marketplaces, and products such as exchange traded derivatives, and crypto currencies.
- Exchanges, Clearing houses, and Collateral
- Exchange traded & OTC derivative landscape
- Crypto currencies dynamics, offerings, and eco system
- Blockchain, AI, and machine learning in trading, finance, and operations
Regulations, Donald Trump, Brexit, and Red Flag Risk Factors- Studying the impacts on the capital markets
- MiFID II: One of the most seismic regulatory shifts in history affecting everything from research to dark pools
- Who will be Bitcoin’s ultimate regulator: Future state of Crypto currency trading regulation
- The Global LEI Initiative – The LEI is part of a much bigger market structure solution
- Deregulation: a lose-lose game that would have serious consequences for the stability of the world financial system
Collateral Tidal Wave: Collateral usage today, tomorrow, and impeding shortfall.
- Account segregation history: MF Global, LSOC, CFTC, CME, and John Corzine
- Instant Payment? Ripple & MoneyGram’s XRP digital currency
- What can China do to help the global collateral exchange?
- Exploring the impact and rule set for non-cleared margin regulation
Crypto-currency evolution, use cases, exploring hype vs. sustainability
- Crypto-currency trading, and the regulatory response
- Case Study: Omega One ,leading crypto-asset agency brokerage for asset managers and institutional investors
- Ethereum and SMART contracts: The winning model for settlement in the future.
- Case Study: Silk Road & Dread Pirate- the complete story- and how the illegal marketplace changed market and trading history
Machine Learning in Finance: A Practical View
- Using machine learning in the new financial markets big data landscape
- Big Data in Finance Landscape
- Infrastructure and technologyData sources
- Modern data analysis – Structured and Unstructured Data & New Models
- Classical and advanced models
- Machine Learning models in practice
- Machine learning robust modeling
- The future of machine learning in finance
Big Data in Finance Landscape
- Big data in finance landscape: Financial modeling, data governance, integration, NoSQL, batch and real-time computing and storage
- Infrastructure and technology
- New data sources
- Modern data analysis: Structured / Unstructured data and new models
Machine Learning Models
- Supervised learning
- Unsupervised learning
- Reinforcement learning
- Deep learning
- Advanced machine learning models
Machine learning in finance – Practice
- Momentum and Mean Reversion
- Sentiment Analysis
- Asymmetric Trading Strategies
- Non Linear Multi-Factor Models
- High Frequency Trading
- Advanced Machine Learning
Machine learning in finance – Opportunities and challenges
- Algo-Grading 101
- Data mining biases: overfitting, survivorship and data-snooping
- Robust trading strategies
- The future of machine learning in finance