Intermarket Analysis Neural Network Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for financial market analysis, particularly in intermarket analysis, lack the ability to accurately predict future market trends using neural networks trained on market data from selected key, general, and predictive intermarkets, leading to inefficiencies in identifying and forecasting price directions.
Innovation Solution
A system and method for performing intermarket analysis by selecting key, general, and predictive intermarkets, processing their data to train neural networks, which then generate predictive output for primary markets, allowing for improved forecasting of future market data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional fundamental analysis or technical analysis methods are used, then analysis simplicity is maintained, but prediction accuracy of future market trends is insufficient
Solution Approach 1:
The patent segments the market analysis system into multiple distinct components: key intermarkets, general intermarkets, and predictive intermarkets. Each segment serves a specific function in the analysis hierarchy, allowing the system to process complex intermarket relationships through structured division while improving prediction accuracy for primary markets.
Solution Approach 2:
The patent introduces a hierarchical dimension to market analysis by organizing intermarkets into three distinct levels (key, general, predictive). This dimensional structure transforms traditional single-level analysis into a multi-layered system that captures complex intermarket relationships, thereby enhancing prediction capability without requiring complete analysis of all possible market interactions.
2Reliability
If all available market data is processed to train neural networks, then prediction comprehensiveness is improved, but processing time and computational resources increase
Solution Approach 1:
The patent extracts and selects only the most relevant intermarkets from the complete set of available markets. By identifying key, general, and predictive intermarkets through systematic selection criteria, the system extracts essential data subsets that maintain prediction reliability while significantly reducing the volume of data requiring processing and training.
Solution Approach 2:
The patent performs preliminary selection and classification of intermarkets before the actual neural network training process. By pre-identifying which markets serve as key, general, or predictive intermarkets, the system prepares optimized data subsets in advance, reducing the computational burden during training while ensuring comprehensive coverage of important market relationships.
3Measurement precision
If neural networks are trained on selected intermarket data, then prediction accuracy for primary markets is improved, but the complexity of network training and optimization increases
Solution Approach 1:
The patent segments the neural network training process into distinct phases corresponding to different intermarket levels. By training networks on separated datasets from key, general, and predictive intermarkets in a structured hierarchy, the system manages training complexity through modular processing while achieving comprehensive prediction accuracy for primary markets.
Solution Approach 2:
The patent performs preliminary data preparation and intermarket selection before neural network training. By pre-processing and organizing intermarket data according to the hierarchical classification, the system simplifies the actual training process while ensuring that networks receive optimally prepared inputs, thereby reducing implementation difficulty despite the sophisticated analysis performed.
Data Source
AI summary
A method and a system for performing intermarket analysis. The method can include, from a pool of available markets in which at least one key intermarket has been selected and removed, selecting at least one market as a general intermarket, and removing the market selected as the general intermarket from the pool of available markets. From the pool of available markets from which the general intermarket has been removed, at least one market can be selected as a predictive intermarket and removed from the pool of available markets. Market data for each of the key intermarket, the general intermarket and the predictive intermarket can be processed to train a neural network. After training the neural network, market data for the primary market can be processed with the neural network to predict future market data for the primary market. The predicted future market data can be output.