Distributed Evolutionary Algorithm for Trading Strategy Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for complex financial trend and pattern analysis, particularly in stock trading, are costly and inefficient due to the need for powerful hardware and centralized infrastructure, making it challenging to process large amounts of historical trading data effectively within a reasonable time.
Innovation Solution
A networked computer system comprising multiple client computers and a server, where each client evaluates genes (trading strategies) based on historical data, with a distributed evolutionary algorithm that assigns genes to classes, evaluates their fitness, and selects surviving genes for further evaluation, allowing for scalable and decentralized processing of trading recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If complex financial trend and pattern analysis is performed using conventional centralized systems, then processing capability is sufficient, but hardware cost and operational cost are significantly high
Solution Approach 1:
The patent divides the centralized computational system into multiple distributed client computers, each performing a portion of the gene evaluation work. The evolutionary algorithm is segmented across the network, with clients independently evaluating different genes or gene subsets, thereby distributing the processing capability across multiple lower-cost devices rather than relying on a single powerful centralized system.
2Power
If complex financial trend and pattern analysis is performed using conventional centralized systems, then processing capability is sufficient, but operational cost is significantly high
Solution Approach 1:
The system segments the computational workload across multiple client computers that can operate independently and in parallel. Each client performs evaluation of genes using its own processing resources, eliminating the need for a single energy-intensive centralized system. The distributed architecture allows for more efficient utilization of available computational resources across the network.
3Quantity of substance
If large amounts of historical trading data are processed in conventional systems, then comprehensive analysis is achieved, but processing time is excessive
Solution Approach 1:
The patent segments the large volume of historical trading data processing into multiple parallel evaluation tasks distributed across client computers. Each client processes specific genes or gene subsets simultaneously, enabling comprehensive analysis of large datasets without the sequential processing bottleneck of conventional systems. This parallel distributed evaluation dramatically reduces overall processing time.
Solution Approach 2:
The system implements continuous evaluation of genes as new data becomes available, rather than batch processing. The evolutionary algorithm continuously adapts and evaluates genes against incoming historical trading data, maintaining constant useful action and reducing total processing time for comprehensive analysis.
4Productivity
If distributed evaluation is implemented, then processing speed is improved, but system complexity increases
Solution Approach 1:
The patent employs a universal gene evaluation framework that can be implemented on any standard client computer with appropriate software. The evaluation logic, fitness functions, and data processing methods are standardized and can be replicated across multiple platforms, reducing the complexity of integrating diverse systems. The universal approach allows different clients to contribute equally without requiring specialized hardware or complex customization.
Data Source
AI summary
A server computer and a multitude of client computers form a network computing system that is scalable and adapted to continue to evaluate the performance characteristics of a number of genes generated using a software application. Each client computer continues to periodically receive data associated with the stored genes stored in its memory. Using this data, the client computers evaluate the performance characteristic of their genes by comparing a solution provided by the gene with the periodically received data associated with that gene. Accordingly, the performance characteristic of each gene may be updated and varied with each periodically received data. The performance characteristic of a gene defines its fitness. The genes may be virtual asset traders that recommend trading options. The genes may be assigned initially to different classes to improve convergence but may later be decided to merge with genes of other classes to improve diversity.