Evai.io: A decentralised, autonomous rating system
for the cryptoasset ecosystem
Many of the ratings issues of the past can be attributed to the centralisation of the rating structures which inevitably leads to bias.
Evai.io seeks to decentralise the ratings process by employing a consensus mechanism to drive upgrades and modifications to the ratings process. Through the use of artificial intelligence and machine learning the Evai ratings process remains autonomous—free of human opinion and bias.
Out of the 9,000+ cryptoassets, few provide any real value or use case. Many projects claim to have a “working product,” though quite often that doesn’t necessarily imply any tangible utility.
The Evai.io ratings system accurately assesses the liquidity of thousands of cryptoassets listed on leading exchange platforms.
Liquidity is calculated using a combination of pricing models developed by the renowned financial academic expert, Professor Andros Gregoriou (University of Brighton.)
Evai cryptoasset ratings are based on a multi-factor model that assesses a wide range of financial risks and variables including momentum, systematic risk, sentiment, volatility, liquidity, and behavioural bias to highlight risks and identify long-term asset value.
How can cryptoasset investors avoid risk and identify long term value in the emerging marketplace?
Development and refinement of in-house algorithmic technologies concentrate on transferability to other asset classes with initial emphasis on cryptoassets.
Artificial Intelligence is used to select and combine indicators with optimal weights to determine the greatest accuracy of each risk factor. The AI software runs daily tests on all indicators, selecting the most efficient with results recorded.
Machine learning techniques are implemented to assess the daily test results and modify the parameters of the AI software. The tweaking of the multi-factor model’s selection criteria will continuously improve the overall accuracy over time.
Evai aims to encourage community engagement and development through a distributed token-based governance system allowing EVAI holders to vote and reach consensus on platform upgrades and security protocols as well as vote on which cryptoasset instruments are added to the ratings platform.
Led by Professor Andros Gregoriou (consultant for the CFA, FCA and the London Stock Exchange) we aim to standardise risk measurement, enabling investors to make clear and informed choices when deploying capital.
Partnership and joint venture arrangements with leading AI research and development teams.
Evai ratings draw from an infinite combination of market factors to determine the most statistically
significant in identifying risk and capturing long term asset value.
The ease with which an asset can be bought and sold without impacting the market price. Liquid assets are normally stable, less influenced by market slippage and easily transferred, making them more appealing to traders.
The community consensus toward an asset or market. Sentiment can be qualified via psychology-based indicators such and the Fear and Greed index. We seek to capture asset sentiment and identify bullish and bearish biases.
Return per unit of risk. This is a fundamental measurement of investment performance. The higher the risk-adjusted return, the better the investment. We use risk measures to identify assets that have performed well compared to those that have underperformed.
The rate of change of an asset's price movement over time. Financial assets experience uptrends and downtrends. Measuring momentum helps ascertain the strength and the continuation of an existing market trend.
Quantifying utility involves determining asset application, adoption, community engagement and development activity. We can measure asset utility and overall quality by analysing metrics such as the number of active addresses, GitHub pull requests, supply distribution and on-chain volume.
Measuring the effect of behavioural biases on asset value. Behavioural economics state that various cognitive biases can introduce market anomalies and impact the intrinsic value of assets. We exploit this hypothesis to measure potential divergences from fundamental value.
Weighing excess to determine asset bubble risk. An asset bubble caused by over-enthusiastic investors increases the chance of reversal. We seek to gauge the probability of a bubble forming and determine the odds of a significant pullback in price.
How correlated an asset is to the broader cryptoasset market. When the market risk is high the asset will magnify the performance of the market. This can reflect positively on price in an uptrend but will pose investment challenges in poor economic conditions.
Determined by the current price multiplied by the circulating supply, market capitalisation is an important determinant of cryptoasset value and demand. We rank assets according to capitalisation and use this as an indicator of potential market performance.
experience within Evai’s constantly evolving platform.