In-house transaction big data graph analysis
Enterprise Big Data Analysis Platform
NetMetrica is a server solution for analyzing large amounts of network data in enterprise environments. It is the time to utilize the big data that is just accumulated in enterprises. Big data in the enterprise consists of master data, transaction data, and unstructured data. Transaction data and unstructured text data, which take up most of them, can be converted into graph (=network) data with proper processing to enable "graph analysis" (=network analysis).
Graph Analysis is an analysis technology that has been selected as the top 10 technology trends in data analysis by Gartner, a market research firm, in 2019. Furthermore, graph features, the result of graph analysis, are a prerequisite for accurate machine learning.
NetMetrica is a server solution for analyzing large graphs in enterprise environments.
Various analysis APIs provided for large-scale analysis can be easily controlled from the GUI-based administrator module, and Python grammar-based scripting environment can be provided to configure and control the analysis flow the way the user wants.
Various Analysis Modules
NetMetrica supports convergence analysis by including statistical analysis and machine learning modules, as well as graph analysis modules such as community identification, influence, connection analysis, and recommendation.
Provide a suitable analysis environment for data scientists
Various analysis APIs provided can be easily called and analyzed through the script management menu.
Specialized in analyzing large network data
NetMetrica excels at analyzing high-volume, complex graph data.
NetExplorer is a solution for visual exploration of network data. It is used to visually explore and analyze network data stored in files and databases.
It is equipped with a tool that can model the data saved as a file as network data, and can model the DB to suit the analysis task and optimize the client to suit the user's task. It is useful for planning and investigation work such as criminal investigation and fraud detection.
Complex network data can be accurately and quickly visualized for exploratory analysis.
|Application Objective||Application Method||Institution Applied to||Application Area|
|Data||Status Analysis||Prediction and Category|
|Telco||Customized marketing and customer behavior prediction||CDR||Identify customer call relationship structure patterns to determine impact on departure avoidance||Customer Clustering||Domestic ‘S’ Telco||Establish marketing strategies using customer behavior data|
|Social Media Analysis||Discover societal issues and predict issue trends||Social Media||•Use word extraction automatically
•Topic extraction and Category Classification
|Predict the rise and fall of the topic||SBS||Polling Agency Brand Marketing|
|Science Technology Trend||Exploring national R&D projects and identifying budget allocations||R&D Information, Thesis, Patents||•Search for Experts in Joint Research Relationships
•Identify the status of convergence research among fields
|–||Korea Institute of Science and Technology Information, National Research Foundation of Korea||Used to identify research trends of R&D research departments and institutions|
|Organization Communication and Cooperation Diagnosis||Identify the current status and problems of collaboration, identify change agents||Email, Messenger, Meeting minutes, and more||•Communication Structure Diagnosis: The Bottleneck
•Discovering Communication Hubs / Influencers
|Classify change agents through machine learning||Domestic ‘H’ Automobile Company, Samsung Electronics||HR|
|Criminal Conduct||Identifying criminal conspiracy through telecommunication and financial transaction history analysis||Call history, accounts, deal transactions||•Expanding suspect groups by automatically navigating mediators
•Visually see the flow of funds / stocks over time인
|–||Supreme Prosecutors’ Office of the Republic of Korea, National Police Agency, Financial Supervisory Service|
|Fraud||Easily track collusion in complex insurance fraud cases||Insurance and claim history||•Find and trace specific patterns
•Calculation of scores for collusion
|–||Life Insurance ‘S’ and ‘K’ Company||Insurance, banks|