I'm working on a very complicated EA now it has Artificial Intelligence using a Neural Network with OpenCL and it's self-learning. On top of that it uses the MQL5 cloud to accelerate calculations, below is some more info on that:
MQL5 Cloud Network Includes Thousands of Computers
The MQL5 Cloud Network consists of nodes - dedicated servers, to which testing agents connect to perform tasks. These nodes are managers (poolers), as they combine agents around the world into larger pools based on their geographical location. Being in the idle mode, each agent sends a message notifying that it is ready to perform a task. The interval between such messages depends on the current load of the MQL5 Cloud Network.
Each node of the network is at the same time treated by MetaTrader 5 as a point to access the MQL5 Cloud Network; a terminal connects to them using the MQL5.com account details. The list of servers of the MQL5 Cloud Network and the number of cloud agents available through them can be found in the terminal, the Tester window, tab "Agents".
An agent is free, that is in the idle mode, in case it is not busy performing its own local tasks received from a local computer or local network. While an agent is busy, it makes no attempt to take tasks from the MQL5 Cloud Network. Within several minutes after completing local calculations, the agent gets in touch with the nearest MQL5 Cloud Network node and offers its services. Thus, your testing agents are working on the network only if you do not need them. And, of course, the agents work on the network in accordance with the set schedule.
Thanks to the ease of installation and the minimum necessary settings of the MetaTrader 5 Agents Manager, thousands of testing agents are available in the network at any given time. The general statistics of MQL5 Cloud Network agents and completed tasks is available on the main page of the project at http://cloud.mql5.com.
If you want to know more about Neural Networks, the link below is the article I used to make my own EA.
The EA isn't ready to use for live trading yet, but the basic code is working now, it has AI, Neural Net, uses OpenCL and accelerates calculations with it in combination with MQL5 cloud services and is self-learning. That's the part I finished today and now I'm testing and optimizing this part, I have a few signals & indicators for now because I have to let the algorithm learn each signal and indicator separately into the EA and let it build a database. Every time it's learning new things and the results are saved in the database so the longer it's building up history the better it gets in trading. Optimizing the EA is fully automated so you won't have to figure out the little differences you can set on your signals anymore because all results are saved and used to make predictions in the future and therefore it gets better in time.
If someone is interested in collaborating with me on this project to make this the best EA in 2015, I'm just 14 days into this and have not much experience in trading maybe 6 months in total so I can use all the help I can get for optimizing the strategy.
Now I'm interested to make an Object-Oriented Expert Advisor from scratch to implement in this EA and using DLL's for communicating with MetaTrader 5 or building databases.
The basic strategy I use now for testing needs an overhaul so that's the first thing I'm going to focus on this week because I have to make the signals from scratch to get it perfect, after finishing the signals the EA has to learn how to use the new variables, after that I have to go through the whole optimization process again before I can begin using this EA for real.
I hope to find someone with trading experience and can do some coding on your own, being creative and willing to collaborate with me on this project. The one who's a serious trader and thinks he or she can be an asset to make this the best system of 2015 with me, you're welcome to contact me and talk about it and maybe even collaborate and use the combined power of two people and make this system best of all.