The limits of the possibilities of artificial intelligence (AI) are still far from being known. This has yet to be proven through a study by researchers from Delhi’s Indraprastha Institute of Information Technology (IIIT) who combined AI with traditional finance to predict cryptocurrency prices.
Make room for the crypto oracle
This study was recently accepted by a well-known academic journal. In fact, Elsevier Information Science confirms the effectiveness of the method developed by the Delhi researchers to predict the prices of cryptocurrencies. This research work was made possible by PhD student Shalini Sharma and her supervisor, Dr. Angshul Majumdar.
The conventional art of predicting the future of assets
There are generally two predominant pricing methods in the financial markets. One is based on the conventional methods of the 1970s. It is the probabilistic approach of Baum-Welch, which makes it possible to predict prices on the financial markets, but also the uncertainty in the forecast.
However, this approach shows its limitations vis-à-vis cryptocurrencies, as information on the underlying events causing the price changes is not available. This is where the modern approach adds value.
Based on AI, this approach is also called deep learning or deep learning. However, the latter does not require any underlying knowledge or information. As a result, it still does not cover the uncertainty variable related to cryptocurrencies.
Read future cryptocurrency prices like on a crystal ball
The observation prior to this study is that there were no tailored methods that supplemented uncertainty for cryptocurrency price predictions.
Shalini Sharma and Angshul Majumdar have pulled out their magic wands for a new approach. Indeed, this solves the problem of forecast uncertainty associated with cryptocurrencies. No better accuracy can be done on the available data. Furthermore, this approach beats all the cutting-edge methods available.
To better understand the method proposed by the Delhi researchers, it is necessary to clarify the notion of CVI. The CVI is nothing more than the volatility index of cryptocurrencies. To this end, it absorbs the fluctuations of a crypto over time. For example, a stablecoin like DAI or USDC will have a lower index than cryptocurrencies like Dogecoin or Shiba Inu.
Therefore, the estimates of uncertainty obtained by the two researchers are related to the historical values of the CVI of the available cryptocurrencies. Consequently, the predictions made through this new method are actually interpretable.
It is a real revolution offered by these two scientists. Indeed, the forecasting methods available prior to their studies were mostly content to be modeled on conventional approaches to financial markets. However, cryptocurrencies, like the blockchain from which they derive, come out of established patterns. It is one more step in the digital revolution that AI offers us.
Get a summary of what’s new in the world of cryptocurrencies by signing up for our new servicedaily and weekly so as not to miss any of the indispensable Cointribunes!
As a finance professional, I consider blockchain a real revolution thanks to all its innovations that have a global impact. It is with passion that I participate in this new digital era through my articles.