MAYA goes beyond this simple architecture and integrates the Algorithmic Trading model with Agile Continuous Deployment and Extreme Programming model, used in ITES industry, to provide a robust IT infrastructure for continuous development and deployment of Trading Algorithms, done with rigor of Software development methodology. MAYA is futuristic in nature and is work in progress as of now.
A model is the representation of the outside world as is seen by the Algorithmic Trading software based system. Financial models usually represent how the algorithmic trading system believes the markets work. MAYA allows construction and validation of trading models using a number of different methodologies and techniques since fundamentally they are all essentially doing one thing: reducing a complex system into a tractable and quantifiable set of rules which describe the behavior of that system under different scenarios. Some of the approaches used in models developed in-house using MAYA include, but are not limited to, mathematical models, symbolic and fuzzy logic systems, decision trees, induction rule sets, probabilistic belief networks, genetic algorithms and neural networks.
The use of mathematical models to describe the behavior of markets is called quantitative finance. Essentially most quantitative models argue that the returns of any given security are driven by one or more market risk factors. The degree to which the returns are affected by those risk factors is called sensitivity. These factors can be measured historically and used to calibrate a model, which simulates what those risk factors could do and, by extension, what returns on the portfolio might be.
Symbolic logic is a form of reasoning which essentially involves the evaluation of predicates (logical statements constructed from logical operators such as AND, OR, and XOR) to either true or false.
Artificial intelligence in Evolutionary Computation models learns using objective functions. Objective functions are mathematical functions which quantify the performance of the algorithmic trading system. In the context of finance, measures of risk-adjusted return include the Treynor ratio, Sharpe ratio, and the Sortino ratio etc. The model component in the algorithmic trading system would be "asked" to maximize one or more of these quantities. The challenge with this is that markets are dynamic. In other words the models, logic, or neural networks which worked before may stop working over time.