Financial decision making and financial risk management involve managing uncertainty. Scenario analysis is a powerful tool for quantifying this uncertainty by generating a large number of future possible evolutions of financial and economic risk variables. Ortec Finance has over twenty five years of experience in applying scenario analysis for leading institutional and private clients worldwide.
In order to continue to meet the requirements placed on the underlying generators of economic scenarios, Ortec Finance has released its next generation Dynamic Scenario Generator (DSG). DSG can provide scenarios for:
- developing strategies to meet long term goals
- implementing these strategies
- managing and monitoring the risk of implemented strategies against the original goals.
DSG provides one consistent framework of scenarios for all these different purposes to prevent having to resort to different scenario models for different applications. This consistency is of crucial importance for the quality of financial decision making and risk management.
Use of scenarios
Scenario properties
 |
DSG employs a unique combination of statistical and econometric techniques which efficiently process vast amounts of time series data. The methodology is a mixture of frequency domain techniques, dynamic factor models and special techniques for dealing with non-normal distributions such as skewness and heavy tails.
|
 |
Risk and return in terms of volatilities, correlations and distributions vary with the horizon. Volatilities increase with the horizon, but typically not following a simple random walk. Instead some variables show lower volatility due to “mean reversion” while others show higher volatility due to “trending behavior”. Both historical data and the scenarios reflect close to zero correlation between equities and inflation on short horizons but a steady increase as the horizon gets longer.
|
 |
Business cycle behavior is observed in all times, countries and variables and shows specific and well documented dynamic relations. For example stock prices tend to crash before GDP goes down which means that stock prices tend to lead the economy. When there are signs of recovery in GDP, unemployment will still be increasing for some time, meaning that unemployment typically lags the economy. Business cycles from the DSG methodology strongly resemble the OECD composite leading indicator.
|
 |
Risk varies over time as volatility itself is highly volatile with specific dynamics and correlations. Both realized and implied volatilities show great deviations from the average volatility on the same sample. Both historical data and the scenarios, show that volatility is negatively correlated with the returns on the underlying value (when volatility is high, returns are low).
|
 |
Risk varies across distributions as dependencies within and between financial markets become stronger as conditions get worse. In both historical data and scenarios, this can be seen from the fact that correlations increase and converge towards a value of one (near perfect correlation) as we move further into the left tails of the distributions. This important feature, by definition, cannot be replicated by a Normal distribution with a fixed correlation.
|
 |
Non-normal distributions are often observed in empirical data on both long and short horizons. The historical data and the scenarios reflect this. Stock returns for example have fat tails and are skewed to the left while the distributions of long term interest rates are skewed to the right.
|