Workflow Completion Time Prediction Using Enriched ML Task Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Enterprises face challenges in providing a clear timeline for account opening due to varied reasons leading to delays, making it difficult to confirm a precise completion time, especially for critical aspects like retail banking, and impacting transparency and real-time status during product origination.
Innovation Solution
Utilizing machine-learning models to predict account opening dates by considering user data, product parameters, and handling stage fluidity within workflows, capturing just-in-time positional information to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual tracking methods are used to monitor account opening timelines, then service agents can process tasks with basic information, but the system cannot provide accurate completion time predictions or real-time transparency to customers
Solution Approach 1:
The patent replaces manual tracking and estimation methods with machine learning algorithms that automatically analyze workflow data, stage transitions, and historical patterns to predict completion times. This substitution of mechanical/manual processes with intelligent systems enables accurate predictions without proportionally increasing operational complexity
Solution Approach 2:
The patent introduces machine learning models as intermediaries between the workflow processing system and the prediction requirement. These models act as mediators that transform raw workflow data into actionable completion time predictions, bridging the gap between basic task tracking and intelligent forecasting
2Measurement precision
If detailed workflow stage data is collected and analyzed in real-time, then accurate completion time predictions can be provided, but the data processing complexity and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing and storing workflow configuration data, stage definitions, and historical completion patterns before prediction is needed. This advance preparation enables the machine learning models to quickly generate predictions during runtime without extensive real-time computation
Solution Approach 2:
The patent segments the prediction process into distinct components: workflow stage identification, data extraction from current stage, historical pattern matching, and completion time calculation. This segmentation allows each component to be optimized independently and processed efficiently in sequence
3Productivity
If basic service request information is used without enrichment, then the processing system remains simple, but the prediction model cannot capture the hidden structures and patterns needed for accurate forecasts
Solution Approach 1:
The patent performs preliminary data enrichment by automatically collecting, organizing, and structuring workflow data, stage information, and historical patterns before they are needed for prediction. This advance data preparation creates a rich feature set for the machine learning models without adding complexity to the core prediction logic
Solution Approach 2:
The patent creates a universal data structure that serves multiple functions: it tracks current workflow stage, stores historical completion patterns, captures product-specific parameters, and provides features for machine learning analysis. This multi-functional data structure eliminates the need for separate systems for each data requirement
Data Source
AI summary
Machine learning techniques are disclosed for predicting a task event such as a service completion event based on a predefined workflow. In one aspect a method includes obtaining initial data for a service request (e.g., an account application), enriching the initial data with data from one or more repositories of an enterprise executing the service request, generating a data structure comprising independent variables extracted from the enriched data, receiving a request for a prediction of a completion time for the service request (e.g., an account opening event) at a first time during processing of the service request in accordance with each workflow, in response to receiving the request for the prediction, inputting the data structure into a machine-learning regression model, predicting, using the machine-learning regression model, a completion time for the service request, and providing the completion time for the service request.