Trade Data to Musical Representation for Pattern Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for technical analysis in finance are time-consuming and fail to identify essential signals or warnings in a timely manner, especially in high-frequency trading environments. Additionally, they are prone to errors due to unsynchronized clocks, lack objectivity, and require significant computational resources.

Innovation Solution

A system and method for processing and monitoring trade data using a computing device that receives trade activity data and user inputs, converts them into training data, and generates a classifier to identify trade irregularities. This system employs metrical trees and audio representations to enhance pattern recognition and reduce computational requirements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If technical analysis methods are used to evaluate investments and identify trading opportunities, then pattern recognition capability is improved, but analysis time becomes excessively long and computational resources are significantly consumed

Engineering Contradiction:
Improvepattern recognition accuracyVSAvoidanalysis time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent transforms trade data from traditional numerical formats into musical parameter representations (pitch, rhythm, timbre, duration). This parameter transformation enables pattern recognition through musical analysis techniques that are computationally more efficient than traditional graphical chart analysis, reducing analysis time while maintaining or improving pattern recognition accuracy.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent replaces traditional mechanical graphical analysis methods (plotting charts, measuring vectors) with an audio-based signal processing system. By converting trade data into audio signals and using spectral analysis, the system achieves faster pattern recognition without the computational burden of graphical methods.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If graphical data visualization techniques are used to process and review trade data, then data analysis capability is improved, but computational resources and storage requirements increase significantly

Engineering Contradiction:
Improvedata analysis capabilityVSAvoidcomputational resources
Core Design Contradiction:
Loss of informationVSUse of energy by moving object

Solution Approach 1:

The patent substitutes graphical visualization with audio visualization. Trade data is converted into audio signals where patterns can be heard rather than seen. This substitution reduces computational resource requirements because audio signal processing is more efficient than graphical rendering and analysis, especially for real-time high-frequency trading data.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the representation parameters of trade data from spatial/graphical dimensions to temporal/audio dimensions. By encoding price, volume, and time information into pitch, rhythm, and timbre parameters respectively, the system enables efficient pattern recognition through musical analysis while reducing storage and processing requirements.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If traditional timestamp synchronization methods are used in high-frequency trading, then time measurement precision is improved, but system complexity and computational overhead increase

Engineering Contradiction:
Improvetimestamp precisionVSAvoidsynchronization system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces musical rhythm as an intermediary representation for time measurement. Instead of directly comparing numerical timestamps, the system converts time intervals into rhythmic patterns that can be analyzed for temporal relationships. This intermediary approach simplifies synchronization by focusing on relative temporal patterns rather than absolute timestamp precision.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent transforms absolute timestamp values into relative rhythmic intervals. By encoding time information as musical rhythm patterns, the system tolerates timestamp imprecision while maintaining the ability to detect meaningful temporal patterns in trade data, reducing the need for complex synchronization mechanisms.

Inventive Principle:
Principle #35Parameter changes

4Loss of information

If human experts manually compare graphs and charts for market surveillance, then subjective evaluation capability is improved, but objectivity and consistency deteriorate

Engineering Contradiction:
Improveevaluation capabilityVSAvoidobjectivity
Core Design Contradiction:
Loss of informationVSReliability

Solution Approach 1:

The patent replaces human subjective visual evaluation with automated audio-based pattern recognition. By converting trade data into audio signals and using computational music analysis, the system provides objective and consistent pattern detection that eliminates human bias while maintaining the expertise of human analysts through trained audio pattern recognition algorithms.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3948475B1Transformation and comparison of trade data to musical piece representation and metrical trees
Publication Date: 2025.04.23 DATA BOILER TECHNOLOGIES LLC
  • EP3948475B1 patent drawingFigure 1
  • EP3948475B1 patent drawingFigure 2
  • EP3948475B1 patent drawingFigure 3

AI summary

A system for processing and monitoring trade data receives and transforms trade activities to a musical piece representation, converts the representation to a metrical tree, and performs analysis that provides more accurate onset detection at accelerated speed with more efficient use of computing resources by placing more emphasis on the information hierarchically contained in the metrical tree than on the tree structure when comparing and matching trade patterns, such as potential market manipulation, market change signal, synthetically created trades, or likelihood that the set of trade activities will result in a market price move of one or more financial assets against plans. The analytical system further weights-in the identified signals and determines scores to reflect likelihood of trade irregularities. When the score does not meet a preconfigured threshold, a corresponding action is executed.