Icon

Just KNIME It S03 _​ CH13 _​ Detecting Fraudulent Contracts

You work in the contracts department of a software company and are asked to detect fraudulent (or wrong) contracts based on their contract value. Given the PDF versions of the contracts, you need to extract their contract value (and, optionally, any other fields you find useful) and detect outliers among them. You can either use simpler outlier detection techniques, such as those based on statistics or visualization, or more advanced ones based on machine learning.

Author: Lada Rudnitckaia

Just KNIME It - Season3 - Challenge 13: Detecting Fraudulent Contractshttps://hub.knime.com/-/spaces/-/~7Gg-3sOHMyeHGru9/current-state/ (1) Tukey's range test JKI S03 CH 13 Detecting Outliers'Tukey's range test' RESULTS (2) DBSCAN Detecting Outliers'DBSCAN' RESULTS (3) Numeric Ouliers Detecting Outliers'DBSCAN' RESULTS get PDFs Content (Tika Parser)from current workflow data area [CWDA]../data/PDF_files/contractsdata set:regex extract contract details exclude $Content$ column outlier detection 'Tukey's range test' (grouped by 'Product')upper == tukey's flagged [data frame]middle == outliers [data frame]lower == chart mosaic [image] (counts bar chart, box-plot)distance definition euclideandensity-based clustering start groupping by 'Product'collect resultsoutlier detection ' DBSCAN' (grouped by 'Product')upper == tukey's flagged [data frame]middle == outliers [data frame]lower == chart mosaic [image] (counts bar chart, box-plot)start groupping by 'Product'collect resultsNode 1374Node 1377Clustercolumnoutlier detection ' Numeric Outlyers' (grouped by 'Product')upper == tukey's flagged [data frame]middle == outliers [data frame]lower == chart mosaic [image] (counts bar chart, box-plot) Read PDFs from CWDA Column Expressions Column Filter Python Script Numeric Distances DBSCAN Group Loop Start Loop End Python Script Group Loop Start Loop End Numeric Outliers Joiner Rule Engine Python Script Just KNIME It - Season3 - Challenge 13: Detecting Fraudulent Contractshttps://hub.knime.com/-/spaces/-/~7Gg-3sOHMyeHGru9/current-state/ (1) Tukey's range test JKI S03 CH 13 Detecting Outliers'Tukey's range test' RESULTS (2) DBSCAN Detecting Outliers'DBSCAN' RESULTS (3) Numeric Ouliers Detecting Outliers'DBSCAN' RESULTS get PDFs Content (Tika Parser)from current workflow data area [CWDA]../data/PDF_files/contractsdata set:regex extract contract details exclude $Content$ column outlier detection 'Tukey's range test' (grouped by 'Product')upper == tukey's flagged [data frame]middle == outliers [data frame]lower == chart mosaic [image] (counts bar chart, box-plot)distance definition euclideandensity-based clustering start groupping by 'Product'collect resultsoutlier detection ' DBSCAN' (grouped by 'Product')upper == tukey's flagged [data frame]middle == outliers [data frame]lower == chart mosaic [image] (counts bar chart, box-plot)start groupping by 'Product'collect resultsNode 1374Node 1377Clustercolumnoutlier detection ' Numeric Outlyers' (grouped by 'Product')upper == tukey's flagged [data frame]middle == outliers [data frame]lower == chart mosaic [image] (counts bar chart, box-plot) Read PDFs from CWDA Column Expressions Column Filter Python Script Numeric Distances DBSCAN Group Loop Start Loop End Python Script Group Loop Start Loop End Numeric Outliers Joiner Rule Engine Python Script

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: RE90273
Created at: 2024-08-09
On NodePit since: 2024-08-11
Last update: 2024-11-21
Created with KNIME version: v4.7.2
Tags: JKISeason3-13TukeyPyRegex

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

Try NodePit Runner!