It was mainly those traders who were able to make money in a difficult year for investors., who relied on Wall Street mathematical models to make decisions take over computer geeks. In a difficult year for investors, when ordinary hedge fund managers lost money, elite traders, who trade based on mathematical models (such trading is called quantitative), stood out against the general background. More than half of the most successful traders and hedge fund managers in 2018 made decisions, using computer algorithms.
This approach to trading will only gain popularity in the future and ultimately will almost completely oust the human factor from the market.In recent years, more and more funds and investment banks are cutting traders and portfolio managers, replacing them with mathematicians, quanta and machines. Famed financier Paul Tudor Jones after being laid off 15% staff of his fund told the remaining staff: No man is better than a machine, and no machine is better than a man with a machine ("No man is better than a machine, and no car is better than a man with a car "). There is every reason to believe, that such an approach to trading will only gain popularity in the future and ultimately will almost completely oust the human factor from the market. To verify this, enough to take a closer look at, What have modern financial markets become?.
Artificial intelligence demonstrates its power again: hedge funds, which use algorithms, become leaders in efficiency ratings, what, Nevertheless, makes mathematicians and programmers the main components of successful investment. Ranked in the top of the reputable annual ranking of the best hedge fund fund managers, compiled by LCH investments (invests in other hedge funds and is part of the Edmund de Rothschild Group), entered DE Shaw, Citadel и Two Sigma. All three companies use the so-called “systematic strategies” – a generally accepted term for decision-making strategies with minimal involvement of the human factor. Non-zero predictability of market fluctuations is quantified by statistical processing of large volumes of observations of the joint behavior of market instruments.
A small video about the work of HFT robots at Citadel Group on the US stock exchange (NYSE,NASDAQ,AMEX). Especially for CNNmoney
I will summarize the preliminary results of the work of the basic version of the robot for S&P-mini and in euros.
По S&P turned out to be a higher frequency machine, more for large lottery, since a short take of 3pp is used. For euro, profit is closed in three stages – 15-30-50ticks with a stop of 10 pips. And deals are much less common.
Below are the work schedules for the year since 05.01.09:
The test used 40 lot by S&P and 6 lot of euros. No super profitability, but filtration is less reliable, and robots show themselves not bad in the long term.
I started to write a robot according to the system that is on the screenshots below… the result is – positions opens and closes where necessary, but there is a downside – opens a bunch of unnecessary deals… have not yet managed to write a system for filtering false inputs, which is essentially the most difficult)))
Simpler with a robot (трендой системе), with take in 4 pips and stop in 6( do not wonder – so it is necessary), the situation is simpler:
Graph from 05.01.00 – on 09.02.2010:
Figures are based on 10 лот, ~ $ 2500 per lot, that with a normal distribution of risk – tobish with a deposit of 10k, this 25% per annum.
I think to focus on a complex robot…but we still need to work with him…)