Navigating the Crypto Market: How SnatchProfits Trading Bots Adapted to the Bear Market

Bitcoin has bounced back to $24,000, potentially signaling the end of the bear market.

It's been a challenging year in the crypto market, with a bear market hitting hard due to geopolitical tensions and the ongoing rate hikes by the Federal Reserve. Bitcoin, which had hit a high of $64,000, tumbled down to $16,000. Despite these challenges, we've been hard at work improving our trading bots and updating our AI models. One major update we made to our AI models was to impro...

Introducing new Telegram Alerts feature to follow live bots trades

It has been almost 2 years since I have started running my Scalp & Swing bots.  These bots trade & hold bitcoin, they are designed only for that. Here are the equity charts: Scalp Bot Swing Bot   ScalpBot has increased bitcoin holdings by around 80% during that time, SwingBot hit a bit less it is about 40%. But the best thing is increasing bitcoin while b...

Scalp & Swing bots BTCUSD trading systems explanation

It’s time to cover how my automated trading systems work. What are their strengths and what are their weaknesses. I call one of the systems the “Swing” system, it trades the way I’d trade myself, with a conservative approach. Another system is called “Scalp”, this is a way more aggressive and way more active system.  Bots use AI signals as brains. Same a...

Market Simulation & Multiple Model Voters for better training & prediction performance

Watching one of Jeremy Howard (fast.ai) videos I’ve heard how his student beat the best result of one of Kaggle AI competitions. It was something with texts. But the guy figured out how to increase training data. It is usual practice in machine learning training for images to augment images, rotate, change colors, add noise so on so you would have the same images but different so AI models c...

Bitcoin technical Features engineering for better AI Time Series forecasting

White running AI tests I figured that I have missing piece in my training / predictive data. By taking any chunk of data from my dataset, that would be 12 hours for short-range AI and 36 hours of data for long-range AI, AI doesn’t know where this knifed out chunk would stand in long term trend. How can it know what has happened a week ago, if it only sees the data from today? I can’t j...

Bitcoin price prediction based on time series predictive AI Model architecture (neural networks)

I want to say thank you to these guys: Jeremy Howard (fast.ai), Jason Brownlee (machinelearningmastery), and Lex Fridman. Most of what I know about machine learning & neural networks is from these guys.  First to apply machine learning on anything you have to figure out what your machine learning objective is. Let's start with this, I have 100 thousand rows of data points collected...

Collecting publicly available Bitcoin market data (features) for predictive machine learning models

What bitcoin price is made of?

It all started with me watching the live Bitcoin price chart and seeing that there are changes between buy-side and sell-side in order books on Bitstamp exchange. I was wondering if there is more money on the buy-side than it is on the sell side, does it mean that price is destined to go up? That’s when I decided that I'm a programmer and I can start collecting snapshots of that and anal...

An Author of SnatchProfits

Hi, my name is Darius Šilkaitis. I have had an interest in computers, business ideas, and the web from a very young age.  I always had a dream to work with neural networks, so-called artificial intelligence technologies. It was just a dream until recently we got breakthroughs in AI. Programming libraries like TensorFlow / Keras / PyTorch became publicly available and now my dreams can...