Top modern research implemented in Python
The solutions, which are available on the market, are often generic, inflexible software, which can be applied to stocks only in a limited scope. Our toolbox is flexible to the largest extent. It is based on modern portfolio theory and implemented using free tools and open-source Python modules. The models can be easily adjusted for any variation of long/short investments, exposure, leverage, list of companies, and the myriad of other tunable parameters for simulation, correlations, probability distributions, optimization, and other involved processes.
Robust macroeconomic modeling
One of the main advantages is that we offer flexible macroeconomic and user-customized modeling when optimizing portfolios. You can choose or accept the prevailing market cycle e.g. recession or late growth. Furthermore, you can include your own expert knowledge of industries and individual stocks in scenario modeling. For instance, you assume that certain industries are to outperform the market in the coming year(s) and volatility will be high in the coming 3-6 months with falling stock markets (SP&500). The modeled behavior of stocks and optimization results will be adjusted accordingly to provide the most optimal solutions specifically for those conditions.
Large Mutual, Hedge Funds and Investment Banks develop such solutions in-house in expert teams. SMEs and private investors don´t have access to these solutions and use classical portfolio optimization models based on many simplified assumptions. For example, as a risk measure is often still used the volatility of a stock (standard deviation) and normality of log-returns is assumed. Tail risks are understated or modeled outright incorrectly. Multiple statistical disadvantages build upon each other and make many of the available software inferior to the offered solutions.