Machine Learning Data Visualization for Automatic Insight Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Developing visualizations for large datasets requires significant time and expertise, as ordinary business users lack the skills to determine which data attributes or types of visualizations best explain a target attribute, making it cumbersome to identify patterns and trends using traditional data reporting mechanisms.
Innovation Solution
The use of computer-implemented machine learning to automatically determine insights, segments, outliers, or other information associated with a dataset, enabling the generation of visualizations without the need for extensive user input, by employing decision trees, information gain, Gini indices, and other machine learning algorithms to identify driving factors and present findings graphically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional data reporting mechanisms are used, then data can be displayed in tables or spreadsheets, but it is difficult to discern patterns and trends and requires significant time and expertise to create visualizations
Solution Approach 1:
The system performs self-service by automatically generating visualizations and insights without requiring user expertise. The machine learning engine autonomously analyzes data attributes, determines relationships, and creates appropriate visual representations, eliminating the need for users to manually select visualization types or manipulate data attributes.
Solution Approach 2:
The patent replaces the mechanical process of manual data analysis and visualization creation with an automated machine learning system. Instead of users manually examining tables and spreadsheets to identify patterns, the system uses computational algorithms to automatically detect patterns, trends, and relationships in the data.
2Measurement precision
If manual data analysis is performed by experienced data scientists, then accurate insights can be obtained, but the process is time-consuming and requires substantial effort from specialized personnel
Solution Approach 1:
The system substitutes the mechanical process of manual data science expertise with automated machine learning algorithms. The machine learning engine replicates and accelerates the analytical capabilities of experienced data scientists by using computational models to identify patterns, segments, and outliers without requiring human intervention.
Solution Approach 2:
The machine learning engine acts as an intermediary between raw data and user understanding. It processes complex data relationships and translates them into actionable insights and visualizations, serving as a mediator that bridges the gap between raw data and meaningful interpretation without requiring users to possess specialized analytical skills.
3Loss of information
If users directly access and analyze large datasets with hundreds of columns and millions of data points, then comprehensive analysis is possible, but it requires skills to manipulate different types and combinations of data attributes
Solution Approach 1:
The system performs self-service by automatically understanding and processing the data structure. The machine learning engine autonomously evaluates hundreds of columns and millions of data points, determining which attributes are relevant and how they should be combined, without requiring users to manually navigate or manipulate the complex data structure.
Solution Approach 2:
The machine learning engine provides universal functionality by handling multiple data types and attribute combinations simultaneously. It can process numerical, categorical, and temporal data together, automatically determining the appropriate analysis approach for each attribute type and their relationships, making the system adaptable to various data structures without requiring specialized user knowledge.
Data Source
AI summary
In accordance with various embodiments, described herein are systems and methods for use of computer-implemented machine learning to automatically determine insights of facts, segments, outliers, or other information associated with a set of data, for use in generating visualizations of the data. In accordance with an embodiment, the system can receive a data set that includes data points having data values and attributes, and a target attribute, and use a machine learning process to automatically determine one or more other attributes as driving factors for the target attribute, based on, for example, the use of a decision tree and a comparison of information gain, Gini, or other indices associated with attributes in the data set. Information describing facts associated with the data set can be graphically displayed at a user interface, as visualizations, and used as a starting point for further analysis of the data set.