Screener by ShezheaNET

This Section is about how Micro AI screens inefficiently priced in tokens on Ethereum.

Screener AI development is fully halted. The IP rights are open for sale. For more information read here.

MicroAI's primary goal is to find and fill capital inefficiencies before the broader market reacts to these inefficiencies. The most inefficient and fastest-paced part of the crypto market is in micro-capitalised tokens. This is also the market where the AI can get results the fastest and thus has a constant flow of feedback to train and improve upon. This constant flow of results is considered here as the price of the token. Increasing the token price and selling the token in time with the calculated planned risk, is thus rewarded. Microcapitalised projects are extremely volatile and have a high degree of social sentiment, demanding a quick result in addition to the large number of data points. MicroAI engages in minimum-capitalised high-frequency trading.

Example: Tokencontract $X is deployed on the Ethereum blockchain. Etherscan verifies the contract. As soon as contract $X is verified, Screener scans the contract and breaks it down into the respective functions. At the same time, the contract creator address is analysed. Here, the transaction history as well as the interacted protocols, CEXs and the portfolio status are considered decisive. As soon as the solidity functions are structured, the contract can be red flagged. A red-flag means that this contract is rated as extremely bad, fake or scam. A red flag means that the contract is immediately discarded and a clear signal for the AI to consider this contract as uninvestable. The token contract $X just discussed is not red-flagged in this example. At this point, the first microtransaction is placed on the Ethereum blockchain. Here, the trading of the token does not yet have to be specifically approved by the contract owner. This makes it possible to invest in the token contract even before the existence of liquidity. As soon as a source of liquidity exists, the microtransaction can be executed automatically. Investing early in token contracts like $X allows a steady cash flow for MicroAI. Now Screener is moving to the next stage. It analyses any metadata of the contract. For example, website links or X-links are filtered out here. The project's websites are searched for any information. Gitbook docs and/or white papers are analyzed for text passages written on GPT, the project is classified in a niche by the general information content and compared with the already existing competitors in the niche. This gives an approximate picture of an actual rating compared to the current rating. At the same time, social sources are used, especially X, by picking out information using the filtering of the ticker $X. All these data points are then sent to the AI, which scores them. If the valuation is good, Screener increases the USD tolerance level for MicroAI, which means that MicroAI can now make a higher capital investment in $X.

Screener itself is not an AI, but an information-seeking script that develops and passes the information in a readable form as data points for the AI. This solves the problem of inefficient AIs that cannot be trained by external data sets because they have an extremely niche use.


(BUSINESS UPDATE) Sale of the technology behind Screener AI

We are open to discussions regarding foreign acquisitions of the technology behind our Screener AI Model. Open Backtesting results and all IP rights will be legally transmitted by Micro Foundation.

Last updated