AI-driven Trading Signal Service

Cointorox will roll out a members-only service for all Cointorox community members. This service features a self-sustainable AI with deep machine-learning capabilities to analyse and predict market movements.

This service will provide members with updates for major trading pairs (BTC-USD, BTC-ETH) — more pairs will be added as the service matures. It will provide updates every 4 hours via Telegram channels — 1 for Long (buy) signals and 1 for Short (sell) signals. At the end of each day, there will be a final call (long or short) which is the result of summarising and evaluating all calls of the day.

There will be 23 agents (bots with different analytical skills) working to continuously analyse and evaluate market data. Over time, the AI (consisting of these 23 bots) will mature and learn the dynamics of the market — hence, we are keeping this service as a BETA at least until early 2020.

Below are some examples from our testings of the AI agents over the past 12 months:

If you are not into the technical side of things, you can stop reading from here.

AI & Deep Machine-Learning Protocol

The following Stacking Models will be used:

  1. Deep Feed-forward Auto-Encoder Neural Network to reduce dimension + Deep Recurrent Neural Network + ARIMA + Extreme Boosting Gradient Regressor
  2. Adaboost + Bagging + Extra Trees + Gradient Boosting + Random Forest + XGB

Active Agents

(These agents will be used synchronously to produce 4-hr calls).

1. Turtle-trading agent
2. Moving-average agent
3. Signal rolling agent
4. Policy-gradient agent
5. Q-learning agent
6. Evolution-strategy agent
7. Double Q-learning agent
8. Recurrent Q-learning agent
9. Double Recurrent Q-learning agent
10. Duel Q-learning agent
11. Double Duel Q-learning agent
12. Duel Recurrent Q-learning agent
13. Double Duel Recurrent Q-learning agent
14. Actor-critic agent
15. Actor-critic Duel agent
16. Actor-critic Recurrent agent
17. Actor-critic Duel Recurrent agent
18. Curiosity Q-learning agent
19. Recurrent Curiosity Q-learning agent
20. Duel Curiosity Q-learning agent
21. Neuro-evolution agent
22. Neuro-evolution with Novelty search agent
23. ABCD strategy agent

Deep Learning Models

1. LSTM Recurrent Neural Network
2. Encorder-Decoder Feed-forward + LSTM Recurrent Neural Network
3. LSTM Bidirectional Neural Network
4. 2-Path LSTM Recurrent Neural Network
5. GRU Recurrent Nueral NEtwork
6. Encoder-Decoder Feed-forward + GRU Recurrent Neural Network
7. GRU Bi-directional Neural Network
8. 2-Path GRU Recurrent Neural Network
9. Vanilla Recurrent Neural Network
10. Encoder-Decoder Feed-forward + Vanilla Recurrent Neural Network
11. Vanilla Bidirectional Neural Network
12. 2-Path Vanilla Recurrent Neural Network
13. LSTM Sequence-to-Sequence Recurrent Neural Network
14. LSTM with Attention Recurrent Neural Network
15. LSTM Sequence-to-Sequence with Attention Recurrent Neural Network
16. LSTM Sequence-to-Sequence Bi-directional Recurrent Neural Network
17. LSTM Sequence-to-Sequence with Attention Bidirectional Recurrent Neural Network
18. LSTM with Atention Scaled-Dot Recurrent Neural Network
19. LSTM with Dilated Recurrent Neural Network
20 Only Atention Neural Network
21. Multihead Attention Neural Network
22. LSTM with Bahdanau Attention
23. LSTM with Luong Attention
24. LSTM with Bahdanau + Luong Attention
25. DNC Recurrent Neural Network
26. Residual LSTM Recurrent Neural Network
27. Byte-net
28. Attention is all you need
29. Fairseq
30. Dilation CNN + LSTM RNN

This service will stay BETA until at least early 2020 as we test the accuracy and sustainability of the AI bot. During this period, we will only invite Cointorox community members to play around with the bot and test the markets.

Questions? Join the community on