Nval
Nval Technical Briefing
Published May 16, 2023
Supported by IowaEDA and Brale
Overview
NVAL demos pricing infrastructure for illiquid assets, starting with NFTs. Using AI and on-chain data feeds, NVAL produces fair market values for NFTs in near real time — foundational for any financial workflow (lending, borrowing, insuring, trading) on non-fungible assets that have no spot price. NVAL sits as an analytics layer between blockchains (L1s, L2s, cross-chain) and the industries building on top (gaming, sports, trade finance, accounting, lending). Mark (CTO) walks through the REST API documented with OpenAPI: a "try it out" docs UI, a Postman collection, and a CLI all return the same price prediction for a specific NFT (the demo values a Doodle at 3.3 ETH with 96% confidence, sitting between the listed price of 4.2 ETH and the highest offer of 2.8 ETH). A Chrome extension surfaces NVAL prices on OpenSea pages, and the NVAL web app shows floor price, listed price, and price history against actual trade prints. The price-history endpoint returns 52 weekly data points across a year (configurable daily). Feature importance breaks down what drives price — 96% market action for a Doodle, 72% market action + 30% accessory-trait for a CryptoPunk — giving traders a way to understand why NVAL priced an NFT where it did.
0:00 Introduction to NVAL
NVAL is the pricing infrastructure for illiquid assets — starting with NFTs. Using AI and on-chain data feeds, NVAL produces fair market values in near real time — foundational for lending, borrowing, insuring, and trading non-fungible assets where there is no spot price.
1:00 Layer between blockchains and industries
NVAL sits as an analytics layer between the raw blockchain data (L1s, L2s, cross-chain) and the industries building on top (gaming, sports, trade finance, lending, accounting) — turning access to data into usable market information.
2:30 REST API and developer docs
Mark, CTO, demos the NVAL REST API documented with the OpenAPI standard. Authenticated B2B customers hit a docs-site "try it out" UI or use an API key + secret in Postman/CLI to fetch price predictions for specific network+collection+NFT-ID combinations.
3:30 Live doodle price prediction — 3.3 ETH with 96% confidence
The demo prices a specific Doodle at 3.3 ETH with 96% confidence. The NFT is listed on OpenSea at 4.2 ETH with offers around 2.8 — NVAL's prediction lands in between, showing both where the market is mispricing and where the owner is over-asking.
5:00 Chrome extension and web app insights
NVAL's Chrome extension surfaces prices on OpenSea pages. The web app goes deeper: market price, current listed price, floor price, and a time-series price history with predictions overlaid against actual trade prints.
6:30 Price history — daily or weekly granularity
The price-history endpoint returns weekly prices for a specific NFT over the last year (52 data points) — configurable down to daily granularity or extended back to mint. Same contract address, same token ID, same shape via Postman.
8:30 Feature importance — market action vs. traits
Feature importance breaks down which signals drive the price. For a Doodle, 96% is market action and very little is trait-based. For a CryptoPunk, ~72% is market action and 30% is accessory/trait — so traits matter significantly for collectibles with strong art.
11:30 Graphing feature importance over time windows
Feeding the feature-importance response into Google Sheets produces pie charts showing the dominant inputs (one-day window) vs. secondary (two-day window, accessories). Different collections produce strikingly different weightings.
Topics: Capital Markets, Investing & Trading, NFTs
