Machine Learning Online Actions for Predictable Career Progression

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Employees lack a clear, unbiased view of their career progression and current recommendations are often inaccurate and unpredictable, leading to biased decisions based on human judgment.

Innovation Solution

A computerized system using machine learning and linear regression to analyze employee data, cluster similar profiles, and provide dynamic, automated recommendations for career advancement through a graphical user interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If manual recommendation processes are used by human managers or coaches, then personal judgment and feedback can be provided, but biases and inaccuracies are introduced leading to unpredictable decisions

Engineering Contradiction:

Improveautomation of recommendation processVSAvoidaccuracy of career progression recommendations

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The patent replaces the manual mechanical process of human judgment with an automated machine learning system. The ML model processes employee profile data, historical progression data, and organizational data to generate recommendations, eliminating human biases while maintaining reliability through data-driven insights and continuous learning from historical patterns.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system implements feedback loops where recommendation outcomes and employee progression data are continuously fed back into the machine learning model. This allows the system to learn from actual career progression patterns, refine its recommendations, and improve accuracy over time, ensuring reliability while maintaining automation.

Inventive Principle:

Principle #23Feedback

2Ease of operation

If highly manual processes are used for providing career recommendations, then personal feedback can be given, but the process becomes unpredictable and inaccurate with heavy penalties on employees

Engineering Contradiction:

Improveease of obtaining career recommendationsVSAvoidtime for employees to understand career progression

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system enables employees to self-serve by automatically generating personalized career recommendations based on their profile data. The ML model processes employee data and provides actionable insights without requiring manual intervention from managers or coaches, making the process easily accessible and immediate for employees while reducing time loss through automated, instant recommendations.

Inventive Principle:

Principle #25Self-service

3Adaptability or versatility

If human judgment is used to decide career profile status changes, then personal advice can be provided, but biases are introduced and predictability is reduced

Engineering Contradiction:

Improveflexibility in career progression decisionsVSAvoidaccuracy of career progression predictions

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system transforms subjective human judgment parameters into objective data-driven parameters. The ML model uses quantifiable features from employee profiles, historical progression data, and organizational structures to make precise predictions about career progression. This maintains adaptability by considering multiple data dimensions while improving measurement precision through statistical analysis and pattern recognition.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250322366A1System and method of dynamically recommending online actions

Publication Date: 2025.10.16 THE TORONTO DOMINION BANK

AI summary

The present disclosure generally relates to a computer device, method and system utilizing machine learning for capturing and analyzing profile data communicated across a computing environment including but not limited to: each user's profile, online behaviors and career progression path and provides dynamic recommendations of online actions to be performed to reach a desired target state.