ML prediction Oracle

Name of Project:

Algorand ML prediction Oracle

Proposal in one sentence:
Implement Machine Learning algorithm to push prediction on-chain.

Description of the project and what problem is it solving:

The proposal is largely based on our experience with Algorand Blockchain.
Artificial Intelligence on Algorand

Algo AMM — Automated Prediction Market Maker on Algorand (Algorand Hackathon prize winner)

A convergence of breakthrough technologies in big data and data analytics provide a critical solution to meet objectives. Big data and advanced analytics play a key role in raising productivity of knowledge-intensive tasks, maximizing assets, and facilitating personalized digital experience.

Predictive process monitoring at runtime is especially growing in importance. Predicting the remaining cycle time, compliance, sequence of process activities, the final or partial outcome, or the prioritization of processes helps organizations to make decisions and gain valuable insights in a rapidly evolving environment.

As transaction volume gradually increases on-chain we would argue that there is a need to reliably assess the market conditions to make an informed decision.
Hence, we propose to implement a machine learning algorithm off-chain that collects transactions data using Python and publishes prediction on-chain with the help of L2 like blockchain and smart contracts.

Grant Deliverables:

  • Pyteal contract on algorand testnet
  • Python library:
  1. to connect to algorand indexer and ETL necessary data
  2. make just-in-time machine learning prediction
  3. update contract on each new prediction
  • brief research analysis on limitations and foreseeable improvements

Found the link to the Algo AMM presentation vie medium article: Encode x Algorand Hackathon: Algo AMM - YouTube