Forecast Engine for Task Completion Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for forecasting task completion rely on subjective estimates, leading to inaccurate projections and inefficient resource planning due to the lack of data-driven approaches.

Innovation Solution

A data processing system utilizing a forecast engine that applies machine learning techniques to predict task completion rates by analyzing historical data, smoothing, and calibrating completion rates using isotonic regression to provide more accurate projections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional subjective estimation methods are used for forecasting task completion, then the process is simple and quick, but the accuracy of projections deteriorates

Engineering Contradiction:

Improveaccuracy of task completion projectionsVSAvoidcomplexity of forecasting system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical/manual system of subjective human estimation with an automated machine learning system that objectively analyzes historical task completion data. The forecast engine uses algorithms to process historical records and generate predictions, eliminating reliance on individual gut feelings while maintaining operational simplicity through automated workflows.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The forecasting system performs self-service by automatically gathering historical data, computing completion rates, selecting relevant attributes, and generating projections without requiring manual intervention. The system serves itself by continuously learning from historical patterns and adapting its predictions based on computed metrics.

Inventive Principle:

Principle #25Self-service

2Reliability

If conventional aggregation of individual estimates is used, then resource planning can be performed, but the reliability of projections deteriorates due to inaccurate input data

Engineering Contradiction:

Improvereliability of task completion projectionsVSAvoidtime required for data collection and processing

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously collecting and storing historical task completion data in advance, so that when forecasting is needed, the data is already organized and ready for analysis. The forecast engine pre-computes completion rates and maintains historical records, eliminating the need for time-consuming data collection at the moment of projection.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring actual task completion outcomes and using this information to refine future predictions. The forecast engine learns from historical patterns and adjusts its modeling based on actual versus predicted performance, improving reliability over time through iterative feedback loops.

Inventive Principle:

Principle #23Feedback

3Productivity

If manual gathering of estimates from multiple individuals is used, then flexibility in customization is maintained, but productivity of the forecasting process deteriorates

Engineering Contradiction:

Improveefficiency of forecasting processVSAvoidease of implementing customized forecasts

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The forecast engine is designed with universal functionality that can handle multiple forecasting scenarios and attribute types through a single system. It can compute completion rates across different dimensions (individual, team, project types) and adapt to various customization needs without requiring separate manual processes, thereby maintaining ease of operation while dramatically improving productivity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10430239B2Method and system for predicting task completion of a time period based on task completion rates of prior time periods using machine learning

Publication Date: 2019.10.01 CLARI INC

AI summary

A request is received from a client for determining task completion of a first set of tasks associated with attributes, the first set of tasks scheduled to be performed within a first time period. For each of the attributes, a completion rate of one or more of a second set of tasks is calculated that are associated with the attribute. The second set of tasks has been performed during a second time period in the past. An isotonic regression operation and/or temporal smoothing are performed on the completion rates associated with the attributes of the second set of tasks that have been performed during the second time period to calibrate the completion rates. Possible completion for the attributes of the first set of tasks to be performed in the first time period is calculated based on the calibrated completion rates of the second set of tasks.