Icon

CI_​IA_​Bank reconciliation - Outliers detection

The aim of this workflow is to detect unreconciled transactions between the accounting system and the bank.

This flow goes through three stages:
- One-to-one matching
- Preparing unreconciled data
- One-to-many matching using DBSCAN and vectorisation of descriptions via BERT.

Read and Preprocess data Matching Reporting Source = 1Source = 2Bank dataAccountancy data Column Expressions Column Expressions One-to-one Matching Reportunreconciled data Preparingunreconciled data Many-to-ManyMatching via DBSCAN Excel Reader Excel Reader Read and Preprocess data Matching Reporting Source = 1Source = 2Bank dataAccountancy dataColumn Expressions Column Expressions One-to-one Matching Reportunreconciled data Preparingunreconciled data Many-to-ManyMatching via DBSCAN Excel Reader Excel Reader

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: driss
Created at: 2023-05-21
On NodePit since: 2023-08-27
Last update: 2026-01-23
Created with KNIME version: v4.7.2
Tags: Internal controlFinancebank reconciliationbertdbscan

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

Try NodePit Runner!