Classification Model Cut-Off Score Adjustment Interface

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current systems lack an efficient method to determine the optimal proportion of users in a target population to expose to a stimulus based on predicted responses, balancing the number of targeted users with the potential detriment of employing the stimulus.

Innovation Solution

A computer-program product and method that utilize a classification model to predict user responses, displaying a graphical representation with options to adjust the cut-off for exposing users, allowing for the determination of the proportion of users to receive the stimulus, and issuing indications on using the model for stimulus exposure based on predefined quality categories.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the proportion of users exposed to the stimulus is increased to improve response rates, then the number of targeted users who respond increases, but the detriment to users from stimulus exposure increases

Engineering Contradiction:

Improveresponse rateVSAvoiddetriment to users

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system changes the parameter of stimulus exposure proportion by using a classification model with adjustable cut-off scores. By varying the cut-off score, the system can expose different proportions of users to the stimulus, optimizing the balance between response rates and user detriment. The graphical user interface allows users to adjust the cut-off score to achieve different exposure proportions.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system incorporates feedback through the graphical representation that displays predicted responses and the proportion of users exposed to the stimulus. This feedback loop allows users to see the consequences of their cut-off score selections and adjust accordingly, optimizing the balance between response rates and minimizing user detriment.

Inventive Principle:

Principle #23Feedback

2Quantity of substance

If the cut-off score is adjusted to expose more users to the stimulus, then the number of targeted users increases, but the complexity of determining the optimal proportion increases

Engineering Contradiction:

Improvenumber of targeted usersVSAvoidcomplexity of determining optimal proportion

Core Design Contradiction:

Quantity of substanceVSDevice complexity

Solution Approach 1:

The classification model acts as an intermediary between the raw data and the decision-making process. It processes the data and provides predicted responses, simplifying the complexity of determining the optimal proportion. The graphical user interface further mediates this by providing visual representations and intuitive controls for adjusting cut-off scores.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces complex manual analysis with automated machine learning algorithms. The classification model automatically processes data and generates predictions, substituting manual mechanical analysis with computational methods that are more efficient and less complex to operate.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If a classification model is used to predict user responses, then the accuracy of predicting user responses improves, but the complexity of the system increases

Engineering Contradiction:

Improveaccuracy of predicting user responsesVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the complexity by separating the classification model from the user interface components. The classification model handles the complex prediction logic independently, while the graphical user interface provides simple interaction mechanisms. This segmentation allows the complex model to be encapsulated within a simple interface.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system uses a simplified graphical representation as a copy or abstraction of the complex classification model. This visual representation allows users to interact with the system without needing to understand the underlying complexity, effectively copying the model's functionality in a simplified form for user interaction.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS10482376B1User interface for assessment of classification model quality and selection of classification model cut-off score

Publication Date: 2019.11.19 SAS INSTITUTE INC

AI summary

The computing device generates a classification model providing prediction data indicating predicted users in a target population who will respond to a target stimulus according to a predefined user response category. The computing device displays in GUI a graphical representation of a generated classification model and a plurality of options each specifying one of different objectives for determining a proportion of users in the target population to expose to the target stimulus. The computing device predicts proportion data indicating the proportion of users in the target population to expose to the target stimulus based on the determined location of the cut-off. The computing device issues one or more indications as to whether to use the classification model as a basis for exposing the proportion of users in the target population to the target stimulus according to the proportion data.