For this article on the importance of AI in the crypto industry, I asked Google’s AI Chatbot, Bard, what it thinks the importance of AI is in crypto. In the wake of another cryptocurrency market rally, I also wanted to get Bard’s thoughts on how AI affects the crypto market. The boom in blockchains powered by AI is one thing, but there’s also automated trading and price prediction.
So I asked a couple questions about that as well. The following article is a curated transcript of my prompts and Bard’s answers. Hopefully you will find this an illuminating look at both the fascinating aspects of the blockchain sector and the impressive marvel of large-language model and predictive artificial intelligence or AI programs.
When I prompted Google’s AI chatbot thusly, “Hi Bard, can you tell me what you think is the importance of AI to the crypto industry?” it answered: “Artificial intelligence (AI) is having a major impact on the crypto industry, and its importance is only going to grow in the years to come.”
Five ways AI is being used in the crypto industry
Bard listed five ways that AI is currently being used in the crypto industry: “Automated Trading, Fraud Detection, Risk Management, Compliance, and Customer Service.” The AI chat assistant said three benefits of AI programming in cryptocurrency are: “Increased efficiency, improved security, and reduced costs.”
Automated trading has long been a staple of stock trading on Wall Street. For many years, firms that could afford the equipment and know-how to do so, have used algorithms to trade stocks at super high frequencies over fractions of a second.
Now with the blockchain industry’s data all out in the open, secured, organized, and mediated by cryptographic techniques, the opportunities for making crypto profits through automated trading will be enormous.
This is likely the strongest of the five AI trends in crypto that Bard listed. Incredibly sophisticated automated traders with enormous data sets to work from will manage many a nest egg while working through a smart contract ecosystem increasingly more integrated with these AI traders.
The next strongest on Bard’s list is probably regulatory compliance. Cryptocurrency is a software and organizational design so novel in many of its approaches that it defies most conventional notions of business and even software. It certainly defies conventional regulatory classifications for securities, commodities, cash, and whatever the heck cryptocurrency is.
That’s ironic, given that cryptocurrency, like any software, is so easy to code up and scale features and requirements to entire app ecosystems. Smart contract features on DeFi blockchains like Ethereum, Cardano, and Solana are not only good for designing programmable money. They’re also useful for building regulatory compliance right into decentralized finance apps.
When I asked Bard how prevalent AI trading is at the moment, the algorithmic chatbot cited a report by CryptoCompare that says automated trading bots are projected to command a market in excess of $10 billion by the year 2025.
How AI prediction models project crypto prices
Bard says the fast-growing popularity of cryptocurrencies and the increasing availability of artificial intelligence tools will drive the growth in automated trading:
“There are a number of benefits to using automated trading. First, it can help to reduce the risk of human error. Second, it can allow traders to take advantage of market opportunities 24/7. Third, it can help traders to save time and money.”
It’s true, especially with the sophistication of blockchain scripts, that AI crypto trading bots can reduce human error. They can also handle aspects of trading cryptos that are slow for humans and fast for computers. Plus, while the human crypto investor has to eat, sleep, and take a break from the charts every so often, the AI can work 24/7 without getting tired or needing to take breaks.
Here’s how Bard says AI works to make crypto price predictions:
“Artificial intelligence (AI) can be used to make crypto price predictions by analyzing historical data and identifying patterns. AI models can be trained on a variety of data, including price charts, trading volume, news articles, and social media sentiment. Once a model is trained, it can be used to generate predictions about future price movements.”
CoinPriceForecast, a popular example of a machine learning prediction model for crypto prices, explains that it works using, “prediction models, a set of parameters that the computer can use to make decisions, time series data, media news, regulator activities, coin events (like forks), and traded volumes on the exchanges and their liquidity, etc
Just don’t mortgage the house or bank everything on the say-so of any hot stock tipster, not even an AI shilling the next hottest cryptocurrency using all the shiniest data.
Google’s Bard was careful to leave this disclaimer with one of its answers: “It is important to note that AI-based crypto price predictions are not always accurate. The crypto market is volatile and unpredictable, and even the most sophisticated AI models can make mistakes. As a result, it is important to use AI-based predictions as a guide, not as a guarantee.”
