Neural Network Behavioral Prediction System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Marketing studies and surveys often fail to accurately predict subject behavior due to the subjective nature of questions, which leads to inaccurate statistics, as respondents may misinterpret or over/under-analyze information under pressure or time constraints, resulting in incomplete and inaccurate data.
Innovation Solution
A computer system that combines factual and behavioral data using a clustering engine to form exemplars and a learning module, employing neural network technology for non-linear mapping, allowing for the prediction of subject behavior by selecting appropriate exemplars based on activation values, thereby overcoming the limitations of simple statistical techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If simple statistical techniques are used to combine behavioral and factual data, then the system is easier to implement, but the accuracy of behavioral prediction deteriorates because complex behavioral relationships cannot be unearthed
Solution Approach 1:
The patent replaces simple statistical techniques with neural network technology, substituting a mechanical/mathematical system with an intelligent system capable of non-linear mapping. The neural network learns complex behavioral relationships from data without requiring explicit programming of statistical relationships, thereby achieving higher prediction accuracy while maintaining reasonable implementation complexity.
Solution Approach 2:
The patent changes the fundamental parameters of the data processing approach by transitioning from linear statistical methods to non-linear neural network computations. This involves changing the mathematical transformations applied to behavioral and factual data, enabling the system to capture complex interactions that simple statistics cannot detect.
2Productivity
If questionnaires are used to collect behavioral data, then data collection is easy and quick, but the accuracy of the data deteriorates due to subjective interpretation and respondent bias
Solution Approach 1:
The patent introduces neural networks as an intermediary between raw behavioral data and predictions. Instead of directly using questionnaire responses, the neural network processes and transforms the data, filtering out subjective biases and extracting objective behavioral patterns. This intermediary layer converts subjective respondent inputs into objective behavioral insights.
Solution Approach 2:
The system allows behavioral data to speak for itself through the neural network's automatic pattern recognition, eliminating the need for respondents to consciously interpret or report their behaviors. The neural network self-learns behavioral patterns直接从观察到的数据中, removing human interpretation bias from the data collection process.
3Measurement precision
If neural network technology is used for non-linear mapping, then behavioral prediction accuracy is improved, but the system complexity increases
Solution Approach 1:
The patent segments the complex neural network system into distinct functional modules: a clustering engine for grouping behavioral data, a learning module for non-linear mapping, and a prediction module for generating forecasts. This segmentation makes the complex system more manageable, easier to implement, and simpler to maintain while preserving the accuracy benefits of neural networks.
Data Source
AI summary
The present invention is a computer system that analyses the factual and behavioural data of a group of subjects, extracts the common behavioural patterns from the collection, and is capable of forecasting the behaviour of a new subject when his or her factual data are inputted to the system. It does so by first taking a collection of both the factual data and behavioural data from a group of subjects. A clustering engine is employed to compute a set of exemplars that concisely represent the population. Afterwards, the factual data of a subject, and the corresponding behavioural exemplar that he or she belongs, are fed to a learning module so that it can learn the mapping between the subject's factual data and behavioural exemplar. After learning, the system is able to predict the behaviour patterns when factual data of a new subject is presented.