Cryptocurrency data company Nomics is applying artificial intelligence to the often chaotic world of cryptocurrency trading .
In an announcement on April 23, Nomics introduced an AI system that makes seven-day cryptocurrency price predictions . The firm claims this makes it the first to share crypto asset price predictions generated by a machine learning (ML) based artificial intelligence system.
Clay Collins, the firm's CEO, told Cointelegraph that the predictions are intended for retail investors seeking ML predictions , and should not be taken as gospel:
“These predictions are not investment advice. Crypto asset investments and trading carry considerable risk of loss and are not suitable for all investors. These predictions should be used as one of several indicators to inform opinions on future movements in prices”.
Collins believes that this type of AI can, and will, do more than guess the future price of assets:
“Machine learning will increasingly overlap crypto market data, and financial data in general, to detect fake volume, laundering trading, and to make informed predictions about the future. Today, we are taking the first step toward using machine learning to elucidate cryptodata trends. ”
Nomics' price prediction system is based on a long-term memory ML (LSTM) model . ML systems are not programmed like traditional software, but learn by examining large amounts of data. In this case, the AI was trained using the cryptocurrency price data accumulated by Nomics during its activity.
Wrong data will be published along with predictions
The AI feeds the price predictions to Nomics so that they can be displayed on the website. The company's chief technology officer Nick Gauthier promised that the company will be open when it comes to AI error rate :
“LSTMs are relatively new to the machine learning space, and financial data is notoriously difficult to predict, but we were able to get fairly reasonable predictions, and we are totally transparent about its historical accuracy.”
The Nomics website shows the seven-day expected percentage change from the current price , the seven-day expected price, and the 30-day average error. Collins noted:
“We know that the predictions may be wrong. … But we feel that if we could find a transparent way to do it, then it could be a beneficial signal, along with their own research, to make sense of the Cryptoverse and related price movements. ”
As a recent Cointelegraph analysis explains, companies are increasingly working to improve data transparency and accountability, key components in bringing institutional investors into crypto markets.