Ethereum Fraud Detection Dataset

A dataset containing fraud and valid ethereum transactions (vagifa/ethereum-frauddetection-dataset) [more]

Context

This dataset contains rows of known fraud and valid transactions made over Ethereum, a type of cryptocurrency. This dataset is imbalanced, so keep that in mind when modelling

Content

Here is a description of the rows of the dataset:

Index: the index number of a row
Address: the address of the ethereum account
FLAG: whether the transaction is fraud or not
Avg min between sent tnx: Average time between sent transactions for account in minutes
Avg_min_between_received_tnx: Average time between received transactions for account in minutes
Time_Diff_between_first_and_last(Mins): Time difference between the first and last transaction
Sent_tnx: Total number of sent normal transactions
Received_tnx: Total number of received normal transactions
Number_of_Created_Contracts: Total Number of created contract transactions
Unique_Received_From_Addresses: Total Unique addresses from which account received transactions
Unique_Sent_To_Addresses20: Total Unique addresses from which account sent transactions
Min_Value_Received: Minimum value in Ether ever received
Max_Value_Received: Maximum value in Ether ever received
Avg_Value_Received5Average value in Ether ever received
Min_Val_Sent: Minimum value of Ether ever sent
Max_Val_Sent: Maximum value of Ether ever sent
Avg_Val_Sent: Average value of Ether ever sent
Min_Value_Sent_To_Contract: Minimum value of Ether sent to a contract
Max_Value_Sent_To_Contract: Maximum value of Ether sent to a contract
Avg_Value_Sent_To_Contract: Average value of Ether sent to contracts
Total_Transactions(Including_Tnx_to_Create_Contract): Total number of transactions
Total_Ether_Sent:Total Ether sent for account address
Total_Ether_Received: Total Ether received for account address
Total_Ether_Sent_Contracts: Total Ether sent to Contract addresses
Total_Ether_Balance: Total Ether Balance following enacted transactions
Total_ERC20_Tnxs: Total number of ERC20 token transfer transactions
ERC20_Total_Ether_Received: Total ERC20 token received transactions in Ether
ERC20_Total_Ether_Sent: Total ERC20token sent transactions in Ether
ERC20_Total_Ether_Sent_Contract: Total ERC20 token transfer to other contracts in Ether
ERC20_Uniq_Sent_Addr: Number of ERC20 token transactions sent to Unique account addresses
ERC20_Uniq_Rec_Addr: Number of ERC20 token transactions received from Unique addresses
ERC20_Uniq_Rec_Contract_Addr: Number of ERC20token transactions received from Unique contract addresses
ERC20_Avg_Time_Between_Sent_Tnx: Average time between ERC20 token sent transactions in minutes
ERC20_Avg_Time_Between_Rec_Tnx: Average time between ERC20 token received transactions in minutes
ERC20_Avg_Time_Between_Contract_Tnx: Average time ERC20 token between sent token transactions
ERC20_Min_Val_Rec: Minimum value in Ether received from ERC20 token transactions for account
ERC20_Max_Val_Rec: Maximum value in Ether received from ERC20 token transactions for account
ERC20_Avg_Val_Rec: Average value in Ether received from ERC20 token transactions for account
ERC20_Min_Val_Sent: Minimum value in Ether sent from ERC20 token transactions for account
ERC20_Max_Val_Sent: Maximum value in Ether sent from ERC20 token transactions for account
ERC20_Avg_Val_Sent: Average value in Ether sent from ERC20 token transactions for account
ERC20_Uniq_Sent_Token_Name: Number of Unique ERC20 tokens transferred
ERC20_Uniq_Rec_Token_Name: Number of Unique ERC20 tokens received
ERC20_Most_Sent_Token_Type: Most sent token for account via ERC20 transaction
ERC20_Most_Rec_Token_Type: Most received token for account via ERC20 transactions

Data summary

File 'transaction_dataset.csv'
- Table ‘transaction dataset’ consists of 9841 data rows along 51 dimensions: ‘Column #1’, ‘Index’, ‘Address’, ‘FLAG’, ‘Avg min between sent tnx’, ‘Avg min between received tnx’, ‘Time Diff between first and last (Mins)’, ‘Sent tnx’, ‘Received Tnx’, ‘Number of Created Contracts’ and 41 other dimensions

Size: 922.8 KB Source: Kaggle Last updated: 2021-11-13 00:06

Analysis completed in 8 minutes ()

View

The quick introduction provides a quick view into the dataset automatically analyzed by Inspirient.

View

The top insights report presents the 30 most relevant insights automatically selected by Inspirient. The insights were chosen because they have a high dimension priority and highlight a relevant pattern.

View

The data quality assessment assesses the quality of the input data and prioritizes mitigation steps based on analytical impact and ease of implementation

Explore all 1,409 insights

Explore all insights

Explore more datasets

Analyst-2 explores entire data repositories and data lakes, autonomously analyzing each dataset using the Inspirient Automated Analytics Engine.

If you would like Analyst-2 to surface insights in your company's data repository or data lake, please get in touch!

These analysis results by Inspirient GmbH are licensed under a Creative Commons Attribution 4.0 International License in conjunction with the licence of the source dataset.

Dimension	Priority
For table transaction dataset* in lines 1–9842 of input file transaction_dataset.csv…*
Column #1 Integer Number
Index Integer Number
Address String
FLAG True/False
Avg min between sent tnx Floating Point Number
Avg min between received tnx Floating Point Number
Time Diff between first and last (Mins) Floating Point Number
Sent tnx Integer Number
Received Tnx Integer Number
Number of Created Contracts Integer Number
Unique Received From Addresses Integer Number
Unique Sent To Addresses Integer Number
min value received Floating Point Number
max value received Floating Point Number
avg val received Floating Point Number
min val sent Floating Point Number
max val sent Floating Point Number
avg val sent Floating Point Number
min value sent to contract Floating Point Number
max val sent to contract Floating Point Number
avg value sent to contract Floating Point Number
total transactions (including tnx to create contract Integer Number
total Ether sent Floating Point Number
total ether received Floating Point Number
total ether sent contracts Floating Point Number
total ether balance Floating Point Number
Total ERC20 tnxs Integer Number
ERC20 total Ether received Floating Point Number
ERC20 total ether sent Floating Point Number
ERC20 total Ether sent contract Floating Point Number
ERC20 uniq sent addr Integer Number
ERC20 uniq rec addr Integer Number
ERC20 uniq sent addr.1 Integer Number
ERC20 uniq rec contract addr Integer Number
ERC20 avg time between sent tnx Integer Number
ERC20 avg time between rec tnx Integer Number
ERC20 avg time between rec 2 tnx Integer Number
ERC20 avg time between contract tnx Integer Number
ERC20 min val rec Floating Point Number
ERC20 max val rec Floating Point Number
ERC20 avg val rec Floating Point Number
ERC20 min val sent Floating Point Number
ERC20 max val sent Floating Point Number
ERC20 avg val sent Floating Point Number
ERC20 min val sent contract Integer Number
ERC20 max val sent contract Integer Number
ERC20 avg val sent contract Integer Number
ERC20 uniq sent token name Integer Number
ERC20 uniq rec token name Integer Number
ERC20 most sent token type String
ERC20_most_rec_token_type String

Dimension	Annotations
For table transaction dataset* in lines 1–9842 of input file transaction_dataset.csv…*
Column #1 Integer Number
Index Integer Number	ID
Address String
FLAG True/False
Avg min between sent tnx Floating Point Number
Avg min between received tnx Floating Point Number
Time Diff between first and last (Mins) Floating Point Number
Sent tnx Integer Number
Received Tnx Integer Number
Number of Created Contracts Integer Number
Unique Received From Addresses Integer Number
Unique Sent To Addresses Integer Number
min value received Floating Point Number
max value received Floating Point Number
avg val received Floating Point Number
min val sent Floating Point Number
max val sent Floating Point Number
avg val sent Floating Point Number
min value sent to contract Floating Point Number
max val sent to contract Floating Point Number
avg value sent to contract Floating Point Number
total transactions (including tnx to create contract Integer Number
total Ether sent Floating Point Number
total ether received Floating Point Number
total ether sent contracts Floating Point Number
total ether balance Floating Point Number
Total ERC20 tnxs Integer Number
ERC20 total Ether received Floating Point Number
ERC20 total ether sent Floating Point Number
ERC20 total Ether sent contract Floating Point Number
ERC20 uniq sent addr Integer Number
ERC20 uniq rec addr Integer Number
ERC20 uniq sent addr.1 Integer Number
ERC20 uniq rec contract addr Integer Number
ERC20 avg time between sent tnx Integer Number
ERC20 avg time between rec tnx Integer Number
ERC20 avg time between rec 2 tnx Integer Number
ERC20 avg time between contract tnx Integer Number
ERC20 min val rec Floating Point Number
ERC20 max val rec Floating Point Number
ERC20 avg val rec Floating Point Number
ERC20 min val sent Floating Point Number
ERC20 max val sent Floating Point Number
ERC20 avg val sent Floating Point Number
ERC20 min val sent contract Integer Number
ERC20 max val sent contract Integer Number
ERC20 avg val sent contract Integer Number
ERC20 uniq sent token name Integer Number
ERC20 uniq rec token name Integer Number
ERC20 most sent token type String	Categorical
ERC20_most_rec_token_type String

Ethereum Fraud Detection Dataset

Context

Content

Data summary

File 'transaction_dataset.csv'

Analysis fidelity reduced to speed things up

Quick introduction to this dataset

Top insights discovered in this dataset

Data quality assessment of this dataset

All insights currently in focus, ranked by relevance

Search Tags

User Tags

Source dimensions

Generated dimensions

Methods

Patterns

Hotspots

Stories

Ethereum Fraud Detection Dataset

Context

Content

Data summary

File 'transaction_dataset.csv'

Analysis fidelity reduced to speed things up

Quick introduction to this dataset

Top insights discovered in this dataset

Data quality assessment of this dataset

All insights currently in focus, ranked by relevance