Machine Learning (Keras LSTM and K-Clustering) to predict Bitcon Price

[Vlad.Sas]

I'm trying for some time now to develop a neural network that can predict bitcoin prices. Bitcoin is a great asset for such an experiment because it has fewer fundamentals than the other stocks or derivatives and it relies more on technical analysis than other assets. Nevertheless, it is impacted from time to time by news and other events in the crypto-world.

I am working with TF + Keras and LSTM (Long-Short Term Memory) cells to try and predict future prices.

If I let the network guess freely, without adjusting it to each OHLC Tick, the predictions look like this:




If i adjust it at every point in the dataset, it is needless to say that the graph of predictions is way more precise:


There are few steps I would like to take to improve this

• Factor in Technical indicator (BB, Ichimoku Cloud, SAR, etc...
• Place a factor for fundamental analysis in the dataset (for example, a score for the positivity of the news at that specific tick (0=bad news for btc, 10=great news)
• Collect data from the order books of the largest exchanged and factor in the order book states at every tick
• Unsupervised learning and K-Clustering to find co-relations between bitcon and other foreign currency (for example, it might be that there's an inverse relationship between bitcoin and the Yuan (generally when Yuan drops, Bitcoin rises). K-Clustering can find such relashionships
• Merging all of the above into a trading bot that aims for around 30%-40% return a year

Does anyone pursue such a goal? If yes, would you like to share the accumulated knowledge/ideas?
This is a serious project and currently, only me and a two of my partners are involved in it, but we could sure use some more man-power. I'd also like to know if someone would like to fund such a venture and get involved.

Cheers to you all!

[samsamlh]

Hey !

I worked on a very similar project a few months ago. I used the exact same tools you do to achieve my goal. I gave up as the performances of my model were poor. I figured out that it's not possible to build a model based on technical analysis. You've to take fundamental analysis into account (typically market sentiment)
My input is that you'll have to use Technical Analysis (patterns) + Fundamental Analysis (sentiments) + Adapt it to general Market trends (Bull/Bear/Sideway).
In the end, I stopped using deep learning and use a real time based algorithm to find known patterns. You should look into this kind of algorithm rather than AI.
Analyze what traders are doing, automate, trade faster than them. There is room for newcomers.

Good luck !

[Vlad.Sas]

Hey !

I worked on a very similar project a few months ago. I used the exact same tools you do to achieve my goal. I gave up as the performances of my model were poor. I figured out that it's not possible to build a model based on technical analysis. You've to take fundamental analysis into account (typically market sentiment)
My input is that you'll have to use Technical Analysis (patterns) + Fundamental Analysis (sentiments) + Adapt it to general Market trends (Bull/Bear/Sideway).
In the end, I stopped using deep learning and use a real time based algorithm to find known patterns. You should look into this kind of algorithm rather than AI.
Analyze what traders are doing, automate, trade faster than them. There is room for newcomers.

Good luck !

Ultimately, to create a nice trading bot, I want to use a combination of the two. I'd like my AI to provide the missing "intuition" factor, and the bot to analyze how powerful the prediction is (I'm planning to have more models), based on couple of different ML models, and add the algorithmic trading factor as well.