Icon

01_​Anomaly_​Detection_​Demo

Outlier Dection / Fraud Detection in Contracts

Discover anomalies / irregularities / Frauds(?) in contracts payment amounts via:

- data visualization
- basic stats
- clustering
- isolation forest

Anomaly Detection in ContractsDiscover anomalies in contracts payment amounts via: - data visualization - basic stats - clustering - isolation forest Loading the Contracts 10 contracts as pdf filestransformed into Documentobjects We are going to use RegEx to extract the following informationfrom each contract: - Date: the date, on which the contract was signed - Contract ID: Each document has a 7-charecter ID (e.g. C000058) - Payment Amount`: Each document contain a payment amount Finding outliers via visual and stats Finding outliers via clustering on one or more features Finding outliers via Isolation Forest Finding outliers via basic stats Finding outliersList of outliersExtracting Contract ID, Date and Payment amounts from the texts using RegExBar chart scatter plotbox plot histogramColor on paymentsto [0, 1]z-score|z| > thr?10 levels10 treesGetting the text from PDFs Numeric Outliers Tile View Extract Date, ContractID and Payment Amount via VisualAnalytics Color Manager Normalizer Visualize Clusters via DBSCAN Normalizer Visualize Outliers via z-score Visualize Outliers H2O IsolationForest PDF Parser Anomaly Detection in ContractsDiscover anomalies in contracts payment amounts via: - data visualization - basic stats - clustering - isolation forest Loading the Contracts 10 contracts as pdf filestransformed into Documentobjects We are going to use RegEx to extract the following informationfrom each contract: - Date: the date, on which the contract was signed - Contract ID: Each document has a 7-charecter ID (e.g. C000058) - Payment Amount`: Each document contain a payment amount Finding outliers via visual and stats Finding outliers via clustering on one or more features Finding outliers via Isolation Forest Finding outliers via basic stats Finding outliersList of outliersExtracting Contract ID, Date and Payment amounts from the texts using RegExBar chart scatter plotbox plot histogramColor on paymentsto [0, 1]z-score|z| > thr?10 levels10 treesGetting the text from PDFsNumeric Outliers Tile View Extract Date, ContractID and Payment Amount via VisualAnalytics Color Manager Normalizer Visualize Clusters via DBSCAN Normalizer Visualize Outliers via z-score Visualize Outliers H2O IsolationForest PDF Parser

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: dietzc
Created at: 2015-12-08
On NodePit since: 2023-04-06
Last update: 2024-09-06
Created with KNIME version: v4.7.2
Tags: fraud detectionanomaly detectiontext processingpdf documentspdfoutlier detectioncontracts

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!