Empirical Smart Investor Syndicate
EMPIRICAL SMART INVESTOR

A Deep Learning Artificial Intelligence Automated Trading Algorithm Development Project

“People no longer are responsible for what happens in the market, because computers make all the decisions.”

Michael Lewis, Flash Boys.

Join the excitement of a startup deep learning artificial intelligence automated trading algorithm development project. Led by a trader with ideas backed up with 30 years experience of what worked, works, and will work in the currency markets.

 

For years, many people could not figure out how to monetize the World Wide Web. We are in a similar situation with the emergent technology of deep learning artificial intelligence. 

 

Artificial intelligence (AI), machine learning and deep learning are three terms often used interchangeably to describe software that behaves intelligently. Deep learning is a subset of machine learning, and machine learning is a subset of AI, which is an umbrella term for any computer program that does something smart. In other words, all machine learning is AI, but not all AI is machine learning, and so forth. 

 

Machine Learning refers to a system that can learn from experience and is closely related to computational statistics, which focuses on making predictions using computers. In the past decade, machine learning has given us self-driving cars, practical speech recognition, and effective web search. Many researchers think it is the best way to make progress towards human-level artificial intelligence. 


Many hedge funds started to utilize Artificial Intelligence within the algorithmic trading world. Machine Learning hedge funds already significantly outperform generalized hedge funds, as well as quant funds. Machine Learning systems can be incredibly helpful tools for humans navigating the decision-making process involved with trading and risk assessment. The impact of human emotions on trading decisions is often the greatest hindrance to performance. Algorithms and computers make decisions and execute trades faster than any human can, and do so free from the influence of emotions.


The opportunity for artificial intelligence to revolutionize this industry cannot be overstated. Well-known funds and industry front-runners such as Citadel, Renaissance Technologies, Bridgewater Associates, Two Sigma Investments, D. E. Shaw, Vatic Labs, Winton, Point 72, Voleon Group, and Virtu Financial are pursuing Machine Learning and Deep Learning strategies as part of their investment approach.


Empirical Smart Investor Syndicate members are stakeholders in the Empirical Smart Algorithm Trading Program, an actively developing project using machine learning algorithms that are continuously self-learning from empirical evidence of correlations between data events and chart patterns and corresponding market responses, that have the ability to perceive patterns that have proven successful in the past and exploit predictable behaviors, into an automated algorithmic trading program that will spot opportunity, trade, take profit, and repeat... hundreds of times each day.


The Empirical Smart Algorithm Trading Program will perform trades in the currency markets based on market chart patterns and behaviors as fast and as scalable as possible using high-speed algorithms to predict short-term price movements and profit from minor price changes using machine learning algorithms to scan markets for even the smallest of opportunities to move in and out of positions. Only minor price changes are required due to the vast amount of orders of anywhere from fifty to a few hundred trades in a single day.

 

Algorithms are increasingly improved through the application of machine learning of probability modelling, data visualization, trend observations, sentiment analysis, chart pattern recognition, volume, order flow, and auction market theory, with the goal of discovering repeatable patterns to predict short-term trading opportunities with automated execution of clear entry signals with automated profit targets and stop losses. 


Concept, initial trading capital, research and back-testing of trading algorithms, development of machine learning algorithms, and oversight of algorithm performance is led by Robert Nash, a professional trader that has traded for a living for 30 years trading futures, options, currencies and gold, and previously founded and managed a licensed and regulated hedge fund management company, a boutique hedge fund, an options dynamic hedging operation, and an algorithmic system incubator, and has lived a financially independent lifestyle of travelling the world and living in four countries for 20 of those years. 

 

The Empirical Smart Investor Syndicate is open to new members with similar ambitions for financial independence.

 

Today it is estimated that more than 80% of trading is done by algorithms. Computers make all the decisions and algorithms are trading against algorithms. Algorithms are used for decision making, order generation, and execution without any human intervention, employing aggressive short-term trading strategies on short time frames for opening and closing positions that capitalize on the benefits of automation and speed. 


The term algorithmic trading is often used synonymously with automated trading, algo trading, black box trading, and quantitative or quant trading, that are heavily reliant on complex mathematical formulas and high-speed computer programs that follows a defined set of instructions (an algorithm) to place a trade. The trade, in theory, can generate profits at a speed and frequency that is impossible for a human trader.


The defined sets of instructions are based on timing, price, quantity, or any mathematical model. Apart from profit opportunities for the trader, algo trading renders markets more liquid and trading more systematic by ruling out the impact of human emotions on trading activities. 

Algorithmic trading is where trade orders are managed by high-speed algorithms which typically involve two-sided order placements to benefit from short-term price volatility fluctuations and order flow of the market auction process, and momentum trading strategies where the algorithm starts execution based on a given spike or given moment to 'buy high to go higher' and 'sell low to go lower.' 

 

Put simply algorithmic trading, is about finding effective ways to carry out a lot of trades in a very short space of time. The time it took you to read the last few paragraphs could be used to make hundreds of trades by a computer. On those numbers, you can see why humans don’t stand much of a chance in competition.


It’s easy to see why algorithmic trading is of great use in the forex market, the world’s largest and most liquid market.

Algorithmic trading programs are designed to be able to act upon small movements in currency prices, the sort of movement that would make a few dollars at a small scale but can deliver bigger returns when the trades are numbered in the hundreds. This is how a small move up or down can result in large returns when the right algorithm can identify and react to many different opportunities in a single day, let alone a week or month.

 

Algorithmic trading in forex is, therefore, an exaggerated form of standard forex trading, using complicated algorithms to make big trading opportunities from the smallest of movements. Forex is a market defined by the constant flow of such movements, making it the perfect choice to apply these principles. 

The Empirical Smart Algorithm Trading Program profits from the intra-day micro-trends (in-and-out of trades in a matter of minutes instead of hours). The overall trading strategy involves taking consistent small profits, rather than riding big, flashy run-ups (followed by equally flashy run-downs). If the trade moves in the predicted direction small profits are taken as soon as momentum is lost. This daily strategy creates incremental profits as markets flow back and forth in the overall trend direction. Basically, the idea is to sustain profitability through taking a small expected profit as many times as possible.