Fake Deposit I Counterfeit Card I Insurance Fraud
Tax Evasion I Money Laundering I Subsidy Fraud I Tax Fraud I Smuggling
Hacking I Illegal Information Leakage I Phishing /Smishing I Fake News
G-FDS, Champion of Fraud Detection
Connect with the graph to see all crime signals
Graph DB shows relationships of all transaction
G-FDS is a fraud detection system reinforced with graph technology. An overall network of suspicious activities is provided by connecting the relationships of all data. G-FDS, unlike the existing FDS, is specialized in tracing fraudulent activities within complex relationships and hidden patterns that are difficult to understand.
FDS is commonly used to detect and track down financial and tax-related crimes such as fake deposits, counterfeit cards, insurance frauds, subsidy frauds, and tax evasions.
An AI-based G-FDS detects what existing FDS cannot. The graph is the key.
Standard Rule-based Detection Method
Detects fraudulent activities by following specific rules.
For example, ‘if a transaction volume increases abruptly’
or ‘if it has same IP address as the blacklist’,
the existing FDS will rule it as a probable fraud.
Fraudulent transactions are identified based on
a standardized pattern of data.
A set of rules make it convenient to detect suspicious
patterns and since the target is clear,
the detection process can be done with a simple operation.
However, the rule-based FDS cannot detect a pattern not defined by a set rule.
Complex Behavioral Relationship-based
Data is interconnected in frequent transaction activities.
Thus, fraudulent activity is detected with
behavioral relationship-based analysis.
The advanced graph algorithms detect both the
unstructured data and standardized patterns.
Fraudulent activities are detected based on all
patterns provided by the ‘Motifs Analysis’
technique. It is possible to detect hidden
meanings that deviate from the existing rules.
How G-FDS works
G-FDS analyzes the frequency of patterns and hidden relationships from
numerous transactions accumulated from connected data.
Graph algorithm application process through Motifs Analysis
Motif: Hypothetical patterns (M1, M2, M3..) that can be created with a certain number of nodes (or subgraphs).
If a hypothetical pattern exists among normal and fraudulent activities, it is referred to as ‘motif fingerprint’. The number of repeated fingerprints within the total patterns are counted (Example: M4 = 24 times).
A score is derived from the number of motif fingerprints collected, which will be needed to find the pattern frequency of fraudulent activities. At this time, a score is given a statistical normal distribution, which is called a Z-score (average score). Based on the Z-score, patterns that frequently repeat in both fraudulent and non-fraudulent activities are listed and the differences are compared. If a motif fingerprint with a large difference in frequency is found among them, it is considered a suspicious pattern. The data of this suspicious pattern can be seen as fraud-type sample data and once this type of data is accumulated, it will be used to detect similar patterns and frauds in the future.
How far can G-FDS go?
Introducing the fields G-FDS cover
Detects and tracks down a fake
deposit with a stolen name
of a third party
Tracks the details and
locations of transactions
made with counterfeit or
duplicated credit card
Detects fraudulent activities
conspired by perpetrator(s)
and victim(s) to illegally claim
Detects individual and
corporate tax evasion crimes
such as manipulation and
concealment of incomes,
transactions, documents, and
Subsidy & Tax Fraud
Detects frauds that unlawfully
receive public finances (tax
returns, subsidies) through
Detects activities of smugglers
carrying contraband and drugs,
etc. on behalf of the
Detects criminal activities in the
such as customer account
theft, product information
leakage, illegal transactions,
Classifies and detects patterns
of fake news that indiscriminately
spread on social media
Phishing / Smishing
Detects fraudulent activities of
stealing personal informatio via
phone or text message
pretending to be a financial
Case. Exposing Fake Deposit
This case introduces tracking of a fake deposit under a stolen name of another person. This is an example of discovering a hidden relationship by linking a suspicious account with a number of clients’ various connections and authentication information with graph data. Based on the motif fingerprint, the fake deposit had a history of financial fraud in the past. By visualizing the graph pattern to facilitate real-time monitoring, it was possible to track another suspicious account related to the fake deposit.
Introducing Product and Service
ProductGraph FDS Product
: Graph FDS engine
Graph data-based Motifs Analysis FDS engine
: Graph-based FDS Storage
Efficiently stores and manages graph data
ServiceGraph FDS Service
FDS Data Modeling
Modeling service in the form of graph analysis
ETL Service / Migration
Create new data and transfer existing data for Graph FDS
Data Analysis & FDS Engine Customization
Optimal FDS engine application based on data type