AutoML GUI Workflow for Non-Expert Predictive Model Deployment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning technologies lack user-friendly business intelligence tools and visualization tools, making it difficult for non-expert users, such as data analysts and business analysts, to perform advanced analytics calculations and make informed decisions.
Innovation Solution
An automated machine learning platform with a graphical user interface (GUI) that allows non-expert users to train, deploy, and utilize machine learning models, featuring modules for dataset management, model training, performance evaluation, and deployment, enabling users to specify datasets, select target metrics, and adjust prediction drivers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If machine learning technologies are used for advanced analytics, then predictive capabilities are improved, but user accessibility deteriorates due to requiring expert-level data science knowledge
Solution Approach 1:
The patent introduces an automated machine learning platform that acts as an intermediary between non-expert users and complex machine learning algorithms. The platform includes a graphical user interface that mediates user interactions, automatically handling data preprocessing, model selection, training, and deployment without requiring users to have expert-level knowledge of machine learning techniques
Solution Approach 2:
The system enables non-expert users to independently perform advanced analytics tasks through automated workflows. The platform automatically selects appropriate machine learning algorithms, prepares datasets, trains models, and deploys them to production environments, allowing users to serve themselves without needing expert guidance or intervention
2Ease of operation
If automated machine learning platform is implemented, then ease of operation is improved for non-expert users, but device complexity increases due to multiple modules and processing steps
Solution Approach 1:
The automated machine learning platform is divided into distinct functional modules including data preprocessing module, model selection module, training module, evaluation module, and deployment module. Each module handles a specific aspect of the machine learning workflow, allowing the complex system to be managed through modular components that can be independently developed, maintained, and scaled
Solution Approach 2:
The platform is designed as a universal system that can handle multiple types of machine learning tasks, data formats, and deployment scenarios through a single integrated interface. The graphical user interface provides unified access to diverse machine learning capabilities, allowing the system to perform multiple functions without requiring separate tools or expert configuration
Data Source
AI summary
An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the credentials. A selection of a target metric to predict using the machine learning model can be received, via the graphical user interface, and datasets included in the plurality of datasets that correlate to the target metric can be identified by analyzing the datasets to identify an association between the target metric and data contained within the datasets. The datasets can be input to the machine learning model to train the machine learning model to generate predictions of the target metric, and the machine learning model can be deployed to computing resources in a service provider environment to generate predictions associated with the target metric.