Claim Your Account
Lets get you verified!
Great! You may close this page
after you've sent us the code on ideascale.
You will receive a confirmation once your account is validated
To verify your ownership of this profile,
please send a personal message to
Lido Nation
on ideascale and include the code above.
Login to follow Alex Sierkov
Alex Sierkov
Claim Account
Follow
Bio
Missing Bio. Claim profile to add a bio.
Community Reviews across funding rounds
Funding data last updated
Alex Sierkov Proposals (2)
Rapid Funding with ML Voting Agents
Solution: A rapid-funding process with weekly awards, a simpler pipeline, ML voting agents to reduce voting workload, and human approval of decisions.
Daedalus Turbo - 10x Quicker Sync
Solution: A new download algorithm better utilizing network bandwidth, a quicker algorithm for wallet-history reconstruction, temporary sync apps, and an integration into Daedalus and Cardano Node.
Monthly Reports
Error following
Successfully subscribed. Watch your inbox!
We will check for new reports and deliver them directly in your email.
Your email will not be shared with any 3rd party or be used for anything else.
The project is complete. Additional information can be found in the close-out report and the corresponding video.
Key tasks for August are to make further UI improvements and to prepare a product demo for the Catalyst community.
We're working on the voter UI allowing voters to quickly identify 3 best projects they would like to support in a given rapid-funding cycle. Even at this early stage, thanks to a number of exploration- and discovery-support mechanisms, a user can be satisfied with the selected 3 projects out of several thousand (Fund6, Fund7, and Fund8 proposals are used as a test setting) after just 15-20 minutes of browsing. This is one of the primary KPIs for our proposal - the time it takes for a voter to be satisfied with the selected top 3 projects.
We were able to find a way to overcome the issue of Catalyst Votes not being available for training for Voting Agent models and adjust our plans accordingly. The work has started on the Voter UI. We are using the CA data from Catalyst Funds 6, 7, and 8 as a playground for the project.
At the moment, the focus areas of the work are:
- develop a proposal-exploration UI, allowing voters to quickly create their own top 3 of proposals.
- develop algorithms for construction of community-wide ranking of projects based on individual preferences.
- develop ML models predicting individual preferences to accelerate the process of exploration of available proposals by individual voters.
All future updates related to the project will be published to the following github repository: https://github.com/sierkov/voting-agents
Under the above link the following items are already available:
- A high level overview of the project.
- A discussion of the requirements for the data.
- An initial data set for model training an evaluation based on the Catalyst proposals in Fund6 and Fund7 and the corresponding rating of individual CAs.
The first milestone of the project is to prepare an initial data set to support the development of machine-learning models. Despite the unexpected disruptions reported above, I am happy to inform that an initial data set has been created and published. The data set along with early documentation can be found under the following link: https://github.com/sierkov/voting-agents