AI Trading Signals

This service is exclusively for HYPE Community members and it is a subscription-based service. Please note that this service will stay in a BETA phase until the end of 2019. If you wish to subscribe as a BETA tester for free, please contact BTlead or Leon on Telegram. Telegram Messenger is a requirement to use this service as all signals are sent via a channel on the app.

 

SIGNAL EXAMPLE

Artificial Intelligence with machine-learning capabilities at work.

 

WHY AI?

Artificial Intelligence revolution is upon us. Self-driving cars are fact, chess programs that beat an average professional have been known for a long time. Stock market trading, being unregulated in terms of traders’ methods, will reward those on the cutting edge of research. Best hedge funds may be still be run by humans but if their method is really better, AI will figure it out as well. Besides, most traders do not compete with the best. Just like in the tale where two men are trying to escape from the bear, they need to out run one another, not the bear. Because stock market has so much randomness, it will take traders longer to notice that their opponent is using a superior method.

Another important argument in favour of AI is that most traders specialize in one trading style, be it trend following, mean reverting, fundamental analysis and so on. That is because learning one style is difficult enough, mastering all of them is impossible. When traders start using AI, they suddenly can reach to methods that were not available for them before. By utilizing AI, traders can trade free from their believes, misguided opinions and personal limitations. (Wojtow, Genotick)

 

SIGNAL 1 (BTC/USD, ETH/USD, ETH/BTC) [25 Machine-Learning AGENT SIGNALS] 

1 daily signal provided

Combination of 25 AI/ML signals, evaluating and analysing the BTC/USD, ETH/USD, ETH/BTC markets every 4 hours. In a typical day, it produces 150 signals and all those signals are combined to find a pattern – BUY, SELL or HOLD. Subscribed users will receive 1 daily signal which is a combination/average of the 150 signals of the following day.

Initially, we were only interested in launching SIGNAL 1 (25 AI agents with machine learning capabilities). However, upon testing it for months, we came to a conclusion that it was simply not as effective and intelligent enough particularly during a volatile bull/bear run. Wojtow, the founder of Genotick highlights this issue with Machine-Learning AI bots used to predict stock market data.

One of the main issue with Machine Learning is over-learning. This is due to the fact that in traditional AI algorithms data is fed to a Neural Network multiple times. If the Neural Network can “see” the data more than once, it can learn to react to changes that are not market inefficiencies but just noise. This can be reduced by selecting how much learning is allowed before checking  network’s prediction on out-of-sample data. However, this isn’t perfect as amount of learning on in-sample-data is also data dependent and in the end is just another parameter that must be adjusted.

This does not mean the AI agents are ineffective and useless. It definitely helps traders find a pattern and draws day-to-day market movements more clearly as opposed to not having it in the first place. Therefore, we will keep SIGNAL 1 and provide SIGNAL 2 on top of it to further improve accuracy of the predictions.

 

SIGNAL 2 (BTC/USD, ETH/USD) [GENOTICK + TWEET SENTIMENTS]

More than 1 daily signals provided

SIGNAL 2 is a combination of the Genotick open-source AI bot + Stacked Learner Tweet Sentiment module. Genotick is a well known open-source AI bot which has performed well for traditional stock markets and commodity markets. However, it has performed relatively weakly and rather conservatively when it comes to cryptocurrencies, due to its immense volatility. To improve this, we have added the Tweets-for-Price-Prediction neural network module which is a script for scraping twitter data for predicting stock prices. 

We overcame the problem of machine-learning AIs specially designing the algorithm to be Walk-Forward only. That is, similarly to actual trading in real life, our software trades and learns as it goes along. There is no separate learning and trading modes. Also, to better simulate real life, we forced the algorithm to trade on the market’s next price, instead of its last. This is to simulate a real life delay between analysis and placing a trade.

At the beginning Genotick creates initial systems by randomly choosing instructions, changing their arguments and grouping them into lists. Each system has one list of instructions than can be up to 1024 long. Interestingly, once a system is created it never changes. This allows us to trust the system – its output will always be the same on the same data. All systems are saved in a population which is adjusted (or “learns”) over time with genetic algorithm, one day at a time.

Our algorithm assumes that there are multiple systems, each a little bit different. We then take all their predictions to calculate one cumulative prediction that would be used by a user to put a trade on. Genotick calculates profit yield by these predictions and reports it to the user at the end. The final result is what a user would get in real life when executing every day and opening a trade at next market open. (Wojtow, Genotick)

 

Genotick Neural Network + Twitter Module

This ensemble learning model combines the predictions of both the market data learner and twitter data learner. Those two learners are used as the base models to train the meta model, a simple multilayer perceptron.

Above Testings Showed a Result of 75% accuracy

From the chart, this network seems to have less of a bias towards a single prediction and might be more suited for practical application. However, the accuracy is not always guaranteed and it is a well-known fact that accuracy of these bots drastically decrease with real-time data, particularly when the markets are highly volatile. 

The AI-powered Trading Signals should therefore, only be used to serve as a supportive indication added on to your proven trading strategies. You should not solely rely on the signals provided by these bots to make financial decisions and your own due diligence is essential when it comes to trading cryptocurrencies.

 

MORE READS ON GENOTICK AI

CONCEPTS USED BY GENOTICK

ERNEST CHAN’S BLOG ARTICLE ABOUT AI TRADING & GENOTICK

 
 

Become a BETA Subscriber

  • be a registered member of the HYPE community group on Telegram
  • have an address with over 5,000 HYPE
  • agree to use the subscription service at your own risks

 

TERMS YOU SHOULD READ BEFORE SUBSCRIBING

All TRADING involves high risk and YOU can LOSE all or a substantial amount of money. Trading in stocks, futures, or options involves considerable risk. When trading with leverage you can lose MORE THAN your initial deposit.

Trade at your own risk; past performance is not necessarily indicative of future results. The content of this website is for general information and education purposes only and should not be construed as investment advice, trading strategy or invitation to trade. All charts and analysis are purely for educational purposes and do not intend to provide trading advice or recommendations.

HYPE is not a licensed financial adviser and will not accept liability for any loss or damage, including without limitation to, any loss of profit, which may arise directly or indirectly from use of or reliance on the content of this site. Past performance is not a guarantee for future results. Hypothetical or simulated performance results have certain inherent limitations.

Unlike an actual performance record, simulated results do not represent actual trading. In addition the results may have under- or over-compensated for the impact, if any, of certain market factors, such as lack of liquidity. Trading programs in general are also subject to the fact that they are designed with the benefit of hindsight. No representation is being made that any account will or is likely to achieve profits or losses similar to those shown.

All profit and loss mentioned on this website is hypothetical only unless stated otherwise. Trading signals presented on this site are for educational purposes only and should not be used as an investment advice. Historical prices used by this site are not verified and may be incorrect and / or incomplete. Therefore, any trading signals derived from such prices may be incorrect. You are solely responsible for verifying any and all information on this site.

All information on this website is provided with a good faith but there is no guarantee to its accuracy and / or correctness. By using this site you agree to store information on your computer / electronic device in order to differentiate you between visitors to this site. We have no means to delete such information from your computer / electronic device, therefore you are solely responsible for deleting such information. We store information about you provided by networking protocols and / or your web browser. Any information we store does not allow us to identify you but does allow us to differentiate between visitors to our site. Such information is stored for up to one week.