ALGORITHMIC TRADING PORTFOLIO
This is the only investment fund in the Baltic countries that uses 100% automated technical strategies. Algorithmic trading systems allows certain financial securities to be bought or sold using mathematical algorithms automatically. These systems are formed by analysing historical and current market data using technical analysis and statistical data processing methods.
The Fund’s main advantages are: performs equally well both in rising and falling markets; risk is limited by using dynamic and extensive diversification; trading only highly liquid instruments. More than 2000 trades are filled during a month. Trading models exploit different inefficiencies, strategies work from a few minutes’ to daily or even weekly data. All of it results in an effective risk management which helps to avoid significant losses in financial markets.
Algorithmic Trading Portfolio differs from any typical fund by using extensive diversification through various different financial instruments and applying multiple completely different trading strategies. Thousands of different strategy variations catch trends, react to market waves, find repetitive patterns and seasonalities. These strategies are used for more than 40 different futures contracts. Put together, they create numerous independent trading patterns. Currently more than 350 trading algorithms are used at once. They work on a daily to weekly basis. A single strategy will almost always suffer from periods of zero or negative returns. Having several hundred fundamentally different models in our portfolio allows us to compensate one’s losses with gains of other models. Therefore, whole fund performance is almost always positive with more than 70% of positive months, which results in an almost steady performance. However, risk is not entirely eliminated.
Strategies are very different from each other and profit from completely different market inefficiencies. The main groups are:
- Trend following
- Mean reversion
Trend following is a strategy that is based on an assumption that prices tend to move upwards or downwards over time. Advantage is taken of these market trends by observing the current direction and buying or selling accordingly. Mean reversion is the assumption that a price will tend to move to the average price over time – price moves like a wave. When the current market price is above the average price, the market price is expected to fall and vice versa. If a wave’s crest or trough is correctly detected, profit can be made even when buying in a bearish market or selling in a bullish one. Seasonal trading strategies exploit regular and predictable changes that recur every calendar period. For example, the harvest effect, when agriculture’s prices rise before and fall after the harvest. Miscellaneous trading systems are based on events, artificial intelligence or a mixture of different trading strategies.
At any point, strategy can be long, short or flat, so profits can be generated in rising and falling markets. Some strategies never hold position overnight, some do. Strategies use only technical analysis indicators and pay no attention to fundamental data.
For additional information please watch a video below (unfortunately video is only in Lithuanian language). It is a presentation given by dr. Aistis Raudys on how artificial intelligence helps to profit in investment. During the presentation, it is explained how much of the trading process is done by computers, how algorithms are created and used, which reduce investment risk, and what results are achieved by automatic trading systems.
If you want to download this video, please click here.