The high speed dark side.

The segment of High Frequency Trading is currently designated as the ultimate technology in systems investments, because of the ability to manage orders directly to book on a high speed.

There is much controversy regarding this technology, either for lack of structure and procedures of software development, causing risk of failure, or the misuse of some participants due to the price manipulation caused by these systems.

FCA, British authority, fined by the 1st time a case of market abuse caused by the misuse of high-frequency systems, due to an abusive practice that uses high speed to send and cancel a high volume of orders in the book, pressing prices artificially.

Investment systems: a pragmatic text.

Investment / Trading systems are computer programs that send orders in the capital market. It's technology architecture is designed to support a decision system that sends signals to enter and exit on asset positions (buy and / or sell).

What ensures investment efficiency is the ability of these systems on making profit in the long run with the maximum possible security. The big question when we consider these systems is the ability to evaluate the performance and rank it as sufficient to ensure efficient management.

That is, put another way, how to separate systems that lack credibility on signals generating of which represent a significant result.

Controlling Complexity in Trading Systems.

The development of trading systems can achieve high degrees of complexity. The process of simulating a particular strategy, termed backtesting can be triggered in several stages of optimization, and monitored at various levels of automation.

Developers always seek out new strategies or logical combinations. A system composed of a set of modules, which are interconnected, could trigger many situations.

The algorithmic complexity that can arise from this process is very high and if not taken care of organizing the evolution of codes, it is possible that errors can be observed as recorded in Knight Capital.

Modules that, being in great quantity and interconnected, go through changes at different times, and, may generate imbalances in the flow of information.

Managing Trading Systems: An Automation and Control Point of View.

Capital Market Investments are known as being risky process, requiring an adequate Risk Management (see Financial Risk Management , Volatility vs. Risk, HFT Risk ). Trading Systems are not out of this group, but trading systems have a particular element: It´s a systematic approach. Systematic doesn´t means profitable, however means tractable (see Financial Automation and Control: a new age).

When I say tractable, I’m referring to the mathematical model, where all the variables and parameters are disposal, ensure tracking.

On the tracking list could be included:

Financial Automation and Control: a new age.

Automation is the application of techniques that reduce human labor and maximize production with fewer costs. We can apply automation on every process that we wish to get done fast. On finance, the automation are on the algorithms that we see keeping and retrieving data, report summarizing, data-mining, etc. There´s no doubt that the need of automation is very large. That are so much things that we wish to be done in milliseconds, many simulations, analysis or data processing that we have to prioritize, since that the workforce is limited against the demands.

Trading Systems Improves Market Liquidity

The use of trading systems, in general, is an effective alternative to increase the liquidity of financial markets without, however, raise the speculative risk relatively.

According to a study published in "The Journal of Finance" in February 2011 entitled "Does Algorithmic Trading Improve Liquidity?" Provides a study which argues that the use of trading systems in the U.S. market enhances liquidity and informativeness of orders. In their study estimates that for large stocks in particular, the use of trading systems narrow spreads, reduce adverse selection and reduces the uncovered positions.

Artificial Intelligence Potential on Trading Systems.

Artificial intelligence (AI) really has a potential when we are seeking to improve the performance of trading systems. The most common applications of AI to trading systems is aimed at optimizing the parameters of a particular strategy. An example is the use of genetic algorithms.

AI algorithms are so called because they have an organization inspired by biological processes. The diversity of algorithms classified as AI is significant and they, effectively, seek to enhance the strategy by optimizations and combinations.

BackTesting, the good guy or the bad guy?

On trading system developing, Backtesting is the process of testing a strategy on a financial historical data. However a backtest don´t represent necessarily the real performance of the system. It could easily made a overfitting, changing the parameters of the system, optimizing the system, but not realy outperforming because the parameters are overtrained to precisely this situation, with a high performance imprecision. The process of the system design needs a separate historical data for the data validation process.

The process of Optimization, the quality of the data, the indicators accuracy, for example, are details that must be looked inside. A system response, observed on the backtest graphic can present a very high sensitivity, changing drastically the performance with few parameters changes, indicating an imperfect optimization.

Why Quantitative Investment Outperforms?

Quantitative investments use computer systems to send buy and sell orders of financial assets. Are systems, often possessing artificial intelligence and complex econometric models in their algorithms. Its application is widespread in the U.S. market and on a continuous evolution.

Some Assets and Funds are available to perform this type of investment wisely, but there are few institutions that develop this approach with a significant degree of maturity.

The backtesting results of a carefully conducted and practical application of systems is that will provide the idea of their actual behavior, ie, if will provide positive returns or if the system will always lose in the long run. Its advantage is the ability to perform simulations and optimizations, and thereby enable the evolving investment process using a historical database. 

Optimization in Finance

The application of optimization techniques on corporative environment for analysis and extraction of financial information is intense and works on the edge of the hardware and software technology.

Optimization is the process of changing the system parameters in order to maximize or minimize a given utility function. Generally we see situations we want to maximize profitability and minimize risk or volatility.

The most popular optimization by the market today is the risk versus return model (Markowitz) of a portfolio of assets (stocks, for example). The goal of this optimization is to allocate capital in a basket of assets in a proportion that seeks to maximize return and minimize risk ordispersion. The model is particularly interesting when the objective is to reduce risk, but must be used with caution if the objective is to use as a strategy for asset management, because the estimated profitability presents a very high degree of inaccuracy (the model uses the arithmetic mean of historical returns to estimate future returns). It can be used, for example, a second process, where the pre-selected asset were chosen as another key strategy.

There are other applications of tools in corporate finance, we can mention the optimization of the value of cash balance. The working capital of a company has the primary function of generating liquidity for routine operations and in any institution. A low working capital may incur a significant cost in loans and management fees, as well as excess working capital incur in a opportunity cost, incurring on losing their real value over time. This value will determine precisely the optimal balance between these two demands.

The development of trading systems makes extensive use of optimization methods, and sometimes a level of complexity that would make the algorithmic description impracticable in this post. One of them is the optimization of the parameters of a system when using a window of historical data and performed various backtestings. Can be used in the management of multiple systems. The topic of optimization of trading systems will be addressed again and need a more detail teaching methodology.

The optimization process, however should not be used indiscriminately. The result of an optimization is only one step in a process that often needs to be restarted. It is possible to enumerate many factors for a good optimization, and even more for the validation of the optimization solution generated. You can, for example, achieve a certain solution and actually be very good theoretically, but it can have a high sensitivity to other factors not taken into consideration as a possible variation in the spread, changes in the brokerage fee used in the simulation, etc.