ML Deposit Asset Estimation with Survey Alignment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for estimating total household deposit assets are inaccurate due to limitations in data collection, aggregation, and manipulation.

Innovation Solution

A method utilizing machine learning models to predict deposit assets, followed by mathematical transformations to align with publicly available household asset surveys, and final allocation based on estimated totals to ensure proportionality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional methods of collecting, aggregating, and manipulating data are used, then the process is simple and accessible, but the accuracy of estimating total household deposit assets deteriorates

Engineering Contradiction:

Improveaccuracy of estimating total household deposit assetsVSAvoidcomplexity of data collection and manipulation system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces conventional mechanical data collection and aggregation methods with machine learning models that automatically learn patterns from data. The system uses ML algorithms to predict deposit assets by analyzing various data sources, eliminating the need for complex manual data manipulation while achieving higher accuracy in estimation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces machine learning models as intermediary components between raw data and final estimates. These models act as mediators that process and interpret data, transforming it into accurate predictions of household deposit assets without requiring complex direct manipulation of the underlying data.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If machine learning models are used to predict deposit assets, then estimation accuracy improves, but computational resources and processing time increase

Engineering Contradiction:

Improveaccuracy of deposit asset predictionVSAvoidcomputational resources consumed

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent performs preliminary actions by pre-processing and preparing data before it is fed into machine learning models. This includes cleaning, transforming, and organizing data in advance, which reduces the computational burden during actual prediction and allows for more efficient use of resources while maintaining high accuracy.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If mathematical transformations are applied to align predictions with survey benchmarks, then comparability with public data improves, but processing complexity increases

Engineering Contradiction:

Improvecompatibility with publicly available household asset surveysVSAvoidcomplexity of transformation process

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies mathematical transformations that change the parameters of the predicted values to match the scale and distribution of publicly available survey data. This involves transforming the output of machine learning models through functions that adjust for differences in measurement scales, ensuring compatibility with benchmark data while maintaining the predictive accuracy.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250054004A1Systems and methods for providing machine learning based estimations of deposit assets

Publication Date: 2025.02.13 JPMORGAN CHASE BANK NA

AI summary

In some aspects, the techniques described herein relate to a method including: generating, by a computer program including one or more machine learning models, for an input record, a predicted amount of deposit assets, wherein the predicted amount of deposit assets is for an individual or household associated with the input record; transforming, with a mathematical transformation, the predicted amount of deposit assets to match a corresponding percentile range defined in a publicly available household asset survey or benchmark; determining a final estimate for the predicted amount of deposit assets, wherein the final estimate is determined to be in proportion with an estimated total of individual or household deposits.