Combination Prediction Model for Attribute Accuracy and Interpretability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tools for predicting attributes of complex dynamic systems lack sophistication and accuracy, particularly in domains like aged care pricing and supply chain optimization, where intricate interdependencies of influencing factors are involved.
Innovation Solution
A novel prediction tool that combines supervised learning workflows, specifically integrating neural networks with random forest models, allowing for the visibility of the impact of various factors on the predicted results, thereby enhancing interpretability and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deep learning algorithms are used for prediction, then prediction accuracy is improved, but interpretability and transparency deteriorate due to black box nature
Solution Approach 1:
The system segments the prediction task into two distinct components: a deep learning model for accurate prediction and a separate interpretability module that analyzes and explains the predictions. This segmentation allows each component to specialize - the neural network focuses on accuracy while the interpretation module focuses on transparency, resolving the contradiction between these two requirements.
Solution Approach 2:
An intermediary interpretation layer is introduced between the deep learning model and the user. This intermediary translates the opaque internal representations of the neural network into human-understandable explanations, maintaining the high accuracy of the deep learning model while providing the interpretability that users need.
2Ease of operation
If simple prediction tools are used, then ease of operation is improved, but prediction accuracy and sophistication deteriorate
Solution Approach 1:
The system automatically performs complex data processing, feature extraction, and model training without requiring user intervention. Users simply input their query and receive both predictions and explanations, making the sophisticated deep learning model as easy to use as simple tools while maintaining high accuracy.
Solution Approach 2:
The system performs preliminary processing of data, training of models, and setup of interpretation frameworks before the user needs results. This preliminary action prepares everything in advance so that when users interact with the system, they receive immediate, accurate predictions with explanations without needing to understand or configure the complex underlying processes.
Data Source
AI summary
A computer-implemented method comprising: accessing data related to at least one attribute of at least one item over time; pre-processing the data by encoding the data to provide labelled data; obtaining a set of attribute predictions by applying the labelled data to a combination prediction model, wherein the combination prediction model comprises two or more supervised learning workflows; and determining and displaying a recommended subset of attribute predictions in response to a user selection, wherein the two or more supervised learning workflows comprise: an integrated neural network, and a random forest model.