SINGAPORE, updated on 8 Jan 2023 / Linkedin / Facebook
Learn how Math can unlock the value of big data.
Applying the best-in-class predictive risk analytics to the financial data of the top 100 tech companies such as Apple, Microsoft, Google, Amazon, Tesla, Facebook, etc.
From the leading NASDAQ-100 Risk-Tech Database (since 1985), Finamatrix.NET, which won three global awards in 2018-2019 for Best A.I. Technology.
MINIMUM QUALIFICATIONS
- GCE O-Level or equivalent and above. All technical jargon will be explained in simple language making this course appropriate for all levels.
WHO SHOULD ENROL
- People who want to learn statistical skills in financial markets.
- Individuals with varying risk appetites who want to develop careers in roles such as analyst, trader, etc.
- Entrepreneurs who want to learn more about practical methods in risk management.
COURSE INFORMATION
- Course Title: FORECASTING FINANCIAL MARKETS IN RISK-DATA & ANALYTICS
- Course duration: 9 hours (3 sessions of 3 hours online)
- Course fees: S$225
- Modes of training: Online (Zoom)
- Course Structure: Daily 7pm-10pm
- Trainer: Dr. Lanz Chan, PhD
, Singaporean, 47, ex-UBS banker, fund manager and Professor, has coached more than 5,000 students in universities and in public lectures/programmes and has extensive experience from Macau, Switzerland and Singapore in gaming and financial forecasting industries. Dr Chan welcomes dialogue on topics related to risks.
COURSE OUTLINE
- Understanding Risk Factors & Measurement
vs Gambling
- How to make Decisions with Martingale Strategy
/ Portfolio Risks
- Statistics: Mean / Standard Deviation
/ Variance
/ Skewness
/ Kurtosis
- Defining & Measuring Value-at-Risk
(VaR)
- Risk Measures: Expected Shortfall / Conditional VaR
- More Risk Measures: Marginal VaR
/ Incremental VaR
- Quantifying & Forecasting Risks with Parsimonious Market Models / CAPM
- Other Measures: Covariance
/ Coskewness
/ Cokurtosis
Approach
- Advanced methods: Monte Carlo Simulation
/ Ex-Post (after the event) vs Ex-Ante (before the event) Algorithmic Optimization
(NAS100 ETF + long/short CFD Strategy with data from 1985 to the most recent data, in support of the Financial Modelers' Manifesto
to avoid over-complexity that leads to math-led failures).
HARDWARE & SOFTWARE REQUIREMENTS
- Computer with 4GB RAM and above.
- Zoom
- Google Sheets (optional)
LEARNING MATERIALS
- All materials will be provided digitally.
LEARNING OUTCOMES
- Participants will learn to appreciate how to operationalize an appropriate risk model to assist in financial decisions so as to enhance career options such as analyst, trader, etc.
- Participants will recognize the limitations of complicated models with assumptions of normality in return distributions, in line with the Financial Modelers' Manifesto, to prevent model failures.
- Participants will understand how to create and implement optimization techniques with suitable algorithms (set of instructions) which provide the most useful and robust results.
- Participants will experience that optimization (finding solutions under limited conditions) is the foundation of machine-learning (artificial intelligence) which is integrated with simulation methods that require no assumptions of return distributions.
- Participants will appreciate that analytical skills are transferable across industries with different datasets.
- Participants will be able to access our vGRE* statistics with no expiration for lifelong learning.
- Participants will have access to our alumni community for global networking.
- Participants become members and can join our partner program as a career option.
Key References:
- Risk Management, A Practical Guide, RiskMetrics Group / MSCI (1999).
- Nasdaq Market Simulation: Insights On A Major Market From The Science Of Complex Adaptive Systems. Vincent Darley, Alexander V Outkin (2007).
- Finamatrix.NET Risk-Tech Database; $FIX Risk-Cybernetics Protocol; Genetic-Algorithm Neural-Network (GANN); Atomic Portfolio Selection (APS) MVSK Utility Optimization (1985-2022).
