Technical Whitepaper

AI Price Patterns:
Vector Similarity & Structural Retrieval

A vector similarity approach to discovering truly analogous market regimes — preserving structural nuance where neural networks blur and statistical models average. Interpretable pattern retrieval and probabilistic scenario planning for professional trading.

01. Abstract: The "Glass Box" Approach

Modern markets operate in regimes that legacy models fail to recognize. Neural networks ("Black Boxes") provide signals but lack explainability, making them unsuitable for managing large capital due to compliance and risk management issues. We propose a "Glass Box" AI Price Patterns that indexes market structure using vector similarity search.

Instead of "predicting" the future, our engine instantly retrieves historical precedents for the current situation, providing complete transparency and evidence-based decision making.

Figure 1.0: The "Glass Box" paradigm — transparent historical retrieval vs opaque black boxes.

02. Motivation: Regime Detection & Honest Backtesting

Practitioners need a way to recover historical context: “Where have we seen this kind of behavior before?” Our system searches for similar situations in a high‑dimensional structural space. Crucially, we employ a "Time Machine" methodology for backtesting—rigorous Walk-Forward Analysis with recursive lookups that eliminates look-ahead bias, providing a true measure of strategy robustness.

Recursive Lookups

For every point in the backtest (e.g., Jan 1, 2020), the engine rebuilds its index using only data available up to that moment. It cannot "see" the crash of March 2020 until it happens.

Walk-Forward Validation

We simulate the exact experience of a trader living through history day by day. This exposes how strategies perform during regime shifts, not just on average.

03. Method Overview

Our pipeline ingests market data, derives structure‑aware features, indexes windows into a Graph Memory, retrieves analogous cohorts via multi‑metric similarity, and projects forward quantile envelopes for range‑first planning.

04. VBRL: From Retrieval to Execution

While standard vector search finds similarity, Vector-Based Reinforcement Learning (VBRL) transforms these analogues into a precise execution strategy. By treating historical matches as a "Ground Truth" memory bank, the agent derives a complete trade plan for the current state.

Figure 2.0: AI Tactical Blueprint — Derived from the consensus of 250+ historical analogues.

Dynamic Trade Planning

Instead of a single "signal," VBRL calculates the optimal **Stop-Loss**, **Take-Profit**, and **Holding Horizon** specifically calibrated to the retrieved pattern cohort.

Strategy Edge (VaR)

Provides quantified confidence metrics: win probability, expected return, and downside risk based on actual historical performance of the analogues.

Zero-Lag Learning

Unlike neural networks that require heavy retraining for new regimes, VBRL's memory bank is updated instantly, allowing the agent to adapt to shifts as they happen.

The Innovation

VBRL replaces the "Black-Box" with a statistical consensus engine. Every decision is an auditable lookup, providing the transparency required for professional risk management.

05. Similarity Search & Cross-Market Transfer

The system scales beyond a single instrument. It can retrieve patterns from Bitcoin and test whether analogous structure emerges on Solana, or jointly aggregate matches from BTC, ETH, and SOL to assess whether a cross‑asset consensus edge exists.

Figure 3.0: Transfer and consensus across assets (BTC, ETH, SOL).

Example 1 — Transfer

“Find situations like those seen in BTC and apply to SOL if the structure reappears.”

Example 2 — Consensus

“Find similar structures on SOL, ETH, and BTC and summarize if a consistent edge persists across assets.”

Interpretability: No Black Box Opacity

Traders see the matched patterns, their similarity scores, cohort composition, and forward outcome envelopes—a complete, transparent line from evidence to decision. No hidden layers. No mystery.

Initialize Workspace Return to Dashboard

From Research to Implementation