Time Discount Rate Estimation via Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for measuring time discount rates, such as questionnaires, face challenges in accuracy and burden on respondents, leading to dispersed answer results and high invalid answer rates.

Innovation Solution

A time discount rate estimation apparatus that uses machine learning to calculate an error between standardized user behavior features and ground-truth time discount rate data, reducing the error to accurately estimate the time discount rate without relying on questionnaires.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the self-completed questionnaire method is used, then the burden on respondents is reduced, but the measurement precision deteriorates due to dispersed answer results

Engineering Contradiction:

Improveburden on respondentsVSAvoidaccuracy of time discount rate

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent replaces the mechanical questionnaire-based measurement system with an automated machine learning system that processes digital behavior data. The ML model learns patterns from automated observations of user behavior (such as app usage, interaction patterns, and temporal preferences) to infer time discount rates without requiring manual questionnaire responses, thereby eliminating the burden on respondents while maintaining measurement precision through algorithmic analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces machine learning models as an intermediary between raw behavior data and time discount rate calculations. The ML model acts as a mediator that processes automated behavior observations and transforms them into accurate time discount rate estimates, bridging the gap between easy data collection and precise measurement without requiring direct respondent input.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If the choice questionnaire method is used, then the measurement precision improves, but the burden on respondents increases and measurement time intervals become long

Engineering Contradiction:

Improveaccuracy of time discount rateVSAvoidburden on respondents

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces the choice questionnaire method with automated machine learning analysis of behavior data. Instead of requiring respondents to actively answer multiple questions, the system passively collects and analyzes digital behavior traces (such as timing of interactions, selection patterns, and usage frequency) to infer time discount rates, thereby eliminating the operational burden while maintaining precision through computational analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent enables the system to perform self-service measurement by automatically collecting, processing, and analyzing behavior data without requiring active participation from respondents. The machine learning model autonomously extracts time discount rate information from raw behavior patterns, making the measurement process self-executing and eliminating the need for respondent effort.

Inventive Principle:

Principle #25Self-service

3Measurement precision

If the choice questionnaire method is used, then the measurement precision improves, but the measurement time intervals become long preventing detection of changes

Engineering Contradiction:

Improveaccuracy of time discount rateVSAvoidtime interval between measurements

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements continuous measurement by continuously collecting and analyzing behavior data in real-time. The machine learning model processes streaming behavior data as it occurs, enabling continuous updates of time discount rate estimates without requiring discrete measurement intervals. This continuous action allows immediate detection of changes in time discount rates as they occur.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The patent replaces the periodic mechanical questionnaire administration with continuous automated digital data processing. The machine learning system continuously monitors behavior patterns and updates time discount rate estimates in real-time, eliminating the time delays inherent in scheduled questionnaire administrations and enabling immediate detection of temporal changes.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250148486A1Time discount rate estimation apparatus, machine learning method, time discount rate analysis method, and program

Publication Date: 2025.05.08 NT T INC

AI summary

An object of the present disclosure is to accurately estimate a time discount rate of a user without depending on a measurement method using questionnaires.Therefore, the present disclosure provides a time discount rate estimation apparatus that estimates a time discount rate in a learning phase, the time discount rate estimation apparatus including: a model learning unit configured to calculate an error between a value obtained by standardizing values of a plurality of behavior features of a user and then multiplying each of the standardized values by a model parameter indicating each coefficient serving as a weight and a time discount rate serving as ground-truth data based on an answer by the user and to perform machine learning on the model parameter so as to reduce the error.