Nothing came up for

Forecasting Cardano Native Tokens

$9,900.00 Received
$9,900.00 Requested
Ideascale logo View on ideascale
Problem:

ADAに比べて流通量が少なく、基礎的な要因に複雑に依存しているため、カルダノのネイティブトークンの評価は困難です。

挑戦: F7: A.I. & SingularityNet a $5T market
completed Awarded 1.98% of the fund.
コミュニティ・アドバイザー・レビュー:
3.67 (9)
Yes Votes:
₳ 53,579,626
No Votes:
₳ 4,073,544
Unique Wallets:
139

エクスペリエンス

複雑な環境(例:ネイティブトークンの市場)での行動(例:取引)を改善するための強化学習の応用。

ソリューション

私たちは、複雑なシステムのための機械知能のツールに基づいて、ネイティブトークンの自動評価方法の開発を提案します。

  • download
  • download

Detailed Plan

Since March 1, 2021, the Cardano blockchain has provided support for native custom tokens, which benefit from the same infrastructure and security features as the ADA cryptocurrency. In addition, by sidestepping the requirement of smart contract coding (in contrast with non-native tokens that run on Ethereum) and by being naturally coupled to work on the Cardano blockchain, Cardano native tokens are more efficient, error-prone and offer reductions in transaction costs.

However, the valuation of Cardano native tokens remains a subtle problem, given the fact that they are complex assets which may be backed up on or stand in representation of other underlying assets, services or goods as defined by the token issuer. A further complication in the valuation or forecasting of native tokens ensues from their limited circulation relative to the ADA cryptocurrency.

It is a well known fact that financial markets are complex systems with interesting macroscopic behavior, such non-trivial time correlations, scale invariance and heavy-tailed distributions. Given the myriad non-trivial dependencies and correlations on underlying factors inherent to the market of native tokens, their valuation is not a straightforward matter and may be similarly amenable to understanding from the point of view of complex systems and time series analysis.

Given the spectacular successes of machine learning methods over the past decade for pattern detection and prediction in all kinds of practical and academic applications, we propose the development of machine intelligence systems, based on reinforcement learning methods for complex systems, with the purpose of the valuation and forecasting of Cardano native tokens. This machine learning application promises to reflect the real value of these assets based on the processing of information that is publicly available and relevant to the valuation of said assets, thereby providing a powerful tool for the community, whereby fair assessments of these tokens can be produced with a rigorous and systematic methodology.

The success of this project consists in the development of a practical, user-friendly machine intelligence system for Cardano native token valuation with an accurate performance as a value predictor of said assets.

Impact:

Nelson has met with Singularity.Net to discuss hosting the completed algorithms.

The reinforcement algorithms will provide the Catalyst community with tools to assist in the valuation of Cardano Native Assets. The F7 award will complete gathering of native asset data and correlated signals for prototyping of the machine learning algorithms. A F8 proposal will be submitted to evaluate the performance of the prototype. A F9 proposal will be submitted to demonstrate the tool with users.

Feasibility:

Team Capability: Nelson leads Photrek which has expertise in the development of machine intelligence algorithms for decision-making in complex environments. Zubillaga is an expert in modeling financial systems and is currently developing reinforcement algorithms. He will design the reinforcement algorithms for control of trading bots.

Roadmap:

A six-month plan with three 2-month phases.

  • Phase 1: Research native tokens launches. Who is planning to launch what and when?
  • Phase 2: Research price of existing native tokens and what are the primary influences of those prices.
  • Phase 3: Design the machine learning algorithm.

Total Budget: 9900 USD.

Each phase will be budgeted at 3300.

The project allocations will be: 50% Applied Research, 25% Data Analytics, 25% Reporting to Catalyst and Singularity Communities.

Auditability:

Success will be identification of a set of Native Tokens with significant potential future value and a set of features of the Cardano Ecosystem that are relevant for training forecasting algorithms.

Key Metrics:

  • Number of native tokens analyzed.
  • Number of features identified for forecasting.
  • Number of engagements with community users.

コミュニティ・アドバイザー・レビュー

Addresses Challenge

4 / 5
3 レビュー

Does the proposal effectively addresses the challenge?

コミュニティーレビュー (3)

Commenter gravatar

This is an interesting small project to use reinforcement learning to value illiquid tokens. Seems like a great project and its good to get projects using AI which provide a service to the community. It would be nice to have a more clearly defined deliverable than just design the model. Will it be tested and written up as a report? Will it be deployed and run continuously? Will the code be released?

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_11
Total QA Ratings
26
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Commenter gravatar

Working in the trade of consumer goods, it has come to my attention that the value of an asset in markets is primarily determined by their supply and demand volumes. Training a machine to detect and recognise patterns is an interesting approach. Overview of who launches what and when, accompanied by their initial values is needed in the ecosystem as right now it relies heavily on potential investors to do their own research in trying to find their options and what value those would hold.

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_113
Total QA Ratings
26
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Commenter gravatar

Data gathering is always a good approach for AI and ML. The proposer plans on gathering data and researching all native tokens that exist and tokens that wish to launch on the Cardano ecosystem. This could improve the ecosystem and help investors because the data would be accessible.

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_471
Total QA Ratings
18
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Feasibility

4 / 5
3 レビュー

Given experience and plan presented is likely that this proposal will be implemented successfully

コミュニティーレビュー (3)

Commenter gravatar

The plan is not very - detailed research tokens, design reinforcement model. The proposer claims experience in the space however doesn't provide any qualifications or references other than to the Photrek website. As there are not really any details on what will be implemented, its hard to give it a high likelihood of successful implementation. What does Design the model mean? Are you actually going to fit the model to data and test it? Its not clear to me that reinforcement learning is the right category of algorithms for pricing illiquid securities. This is generally used when you have an environment you can repeatedly simulate and take different action each time to find the best course of action. Valuing illiquid tokens seems more like a classification problem. Find the correlation (or other parametric/non-parametric relationship) between coins and use that to change the value of an illiquid coin when coins it has a relationship with move.

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_11
Total QA Ratings
26
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Commenter gravatar

The project is set to request 3 consecutive funding proposals, each spanning 3 2-month phases, so the entire project would request ~29700 USD over a timespan of a year and a half. The proposers have relevant experience to develop this, along with a team of academic collaborators found on their website.

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_113
Total QA Ratings
26
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Commenter gravatar

Regarding feasibility, the proposal has all the relevant information. The team has the relevant experience needed to develop this. They provide this information on their website. Looking at the detailed plan we see that the proposer plans on proposing again in F8 and F9. This shows that the team has thought about it and has decided to split up the proposal for a better chance at funding. Since this is the first step in their plan to build an AI service for native tokens, we are only focusing on gathering data in this proposal and the roadmap regarding this speaks for itself. The budget is also more than reasonable.

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_471
Total QA Ratings
18
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Auditability

3 / 5
3 レビュー

Does the proposal provides sufficient information to assess and audit progress and completion?

コミュニティーレビュー (3)

Commenter gravatar

We have a good roadmap, the budget breakdown is rudimental but does suffice. The proposal also states key metrics and defines what success is for the team.

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_471
Total QA Ratings
18
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Commenter gravatar

The proposer aims to research the tokens and design a model, however the outputs of this project are not very well defined. Will you implement the model. Train and test it? The proposer has not given any clear metrics for success which can be measured. They have stated that success would be identification of a set of potentially valuable tokens or a set of features useful for valuation. That doesn't line up well with the states goal of valuing the illiquid securities for which the metrics would be accuracy of valuation for an illiquid token which has not traded when a price event occurs against which we then have visibility.

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_11
Total QA Ratings
26
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Commenter gravatar

There is a roadmap, KPI, periodic definition of success and budget breakdown. It isn't entirely clear how the budget breakdown applies to the phases as the timespan does not correspond with the prospected 12 months, so it would be an improvement to provide a short general overview on the entire project. A further improvement would be to shed some light on how the algorithm variables would look like as what you're aiming to do depends on that.

Assessment Quality Assurance

Assessment Quality Assurance is an offered role to veteran in the Cardano Project Catalyst Community. The purpose is to review PA assessments of proposals, providing a second layer of Quality Assurance.

Assessor ID
z_assessor_113
Total QA Ratings
26
QA Rating Outcome
Good
人間性の確認

コメントを書く

Replying to

Monthly Reports

Please change the primary point of contact for the project to Kenric Nelson, [email protected]. Bernardo Zubillaga's availability is uncertain. Further details are in the uploaded project plan.

Disbursed to Date
$9,900
Status
Still in progress
Completion Target
8/31/2022
Attachment(s)

Thank you for the support. The meetings this month with SingularityNET have been inspiring. This has opened up a variety of new opportunities for Photrek to develop capabilities in Machine Intelligence that will support an equitable, free, sustainable planet.

Disbursed to Date
$9,900
Status
Still in progress
Completion Target
8/31/2022

Photrek's customer engagements for FCNT include: a) Six briefings to the SingularityNET community including a presentation to the founder Ben Goertzel. These discussions led to submission of two proposals to SNET's Deep Fund. A $30k proposal will support development of "Risk-aware AI Assessments" and a $115K proposal will support development of a "Risk-aware Data Generator". The conversations identified an important need to simulate gaps in time-series data so that AI training sets can be complete. We are also discussing requirements for agent-based simulations of markets.

b) Photrek met with Rick McCracken of DripDropz to discuss valuation of analysis of newly launched Cardano Tokens. These are ongoing discussions to determine how Photrek's risk analysis capabilities can be applied to supporting the DripDropz process of launching tokens for the Cardano community.

Disbursed to Date
$9,900
Status
Still in progress
Completion Target
8/30/2022

The customer support via SingularityNet and Drip Dropz has allowed Photrek to increase its staffing for development of risk-aware ML methods. As such, Photrek will complete the F7 FCNT project early. The project was originally planned as a six-month project to end August 31st. We are now planning to close-out the project by July 22nd. The new schedule is:

Kenric Nelson and Kevin Chen will host a Catalyst Swarm breakout presentation on July 9th. This session will review the capabilities of the open-source NeuroProphet software for learning models of time-series data, such as crypto markets.

The July report will be submitted between July 11th and July 15th.

A close-out report and video will be completed and submitted by July 22nd.

Disbursed to Date
$9,900
Status
Launched
Completion Target
7/22/2022
Attachment(s)

Schedule for Completion and Next Steps

  1. The FCNT Final Report and Video will be submitted by July 22nd.
  2. Photrek will continue discussions with Drip Dropz and Adosia regarding analytical support for these Cardano development teams. Analysis for Drip Dropz token airdrops will wait for an up turn in the cryptocurrency market. An advisor role for Adosia's work on decentralized IOT is being defined.
  3. Photrek won two SingularityNET DeepFunds that are now underway. "Risk-aware Assessments of AI Algorithms" is a 4-month, $30K project and "Risk-aware Data Generator for SingularityNet Applications" is a 6-month, $115K project.
  4. Photrek has submitted a F9 Dapps, Products, and Integration proposal, "Learning Dynamic Models" that will extend its Coupled VAE architecture to dynamic time-series.
  5. The capabilities initiated under the FCNT project will be applied to work in environmental sciences. In this area Photrek is proposing a Phase II effort to calibrate and integrate sound pollution sensors, and Photrek is rewriting a proposal to the National Science Foundation regarding severe weather forecasting.
Disbursed to Date
$9,900
Status
Launched
Completion Target
1. In the next month
Attachment(s)
EP1: 'd' Parameter
0:00
/
~1:00
1x