Use Case: Private Income Verification

Process Payslips Faster With Intelligent Document Processing

DOWNLOAD CASE STUDY AS PDF
GET YOUR DEMO

Overview

The client is one of the leading providers of consumer loans and leasing for private individuals and small businesses in Switzerland. The bank employs approximately 300 people, with customer loans amounting to over CHF 2 billion.

Task Icon_Case Study | Acodis
Task

Data extraction from payrolls

Scope Icon_Case Study | Acodis
Scope

Over 40'000 documents per year

Services Icon_Case Study | Acodis
Services
OCR, data extraction & validation
"Acodis successfully passed our rigorous risk assessment. Acodis IDP was deployed in record time and after only a few months our credit experts are already using an automated solution for an important part of our credit scoring process."

Head Risk Processes & Framework

Stop struggling with your document processing!

Get in touch with us and learn how you can improve the way your business handles paperwork.

CONTACT US

Starting Point

To apply for a loan, clients must submit various documents, including several pay slips for verification. The bank receives over 10,000 documents a year. The specialists manually record various predefined data points from these documents, check them, and determine a credit score based on the information obtained. Given the large variety of payroll documents with different layouts and structures, a static, template-based approach was out of the question in the past.
 
With the support of intelligent document processing (IDP) expert, Acodis, a new attempt was made to automate the process with the aim of introducing process-supporting software for automated payroll data extraction.

Get the Full Case Study as a PDF

DOWNLOAD CASE STUDY AS PDF

Our Approach

After setting up a representative training set of 1,300 payslips, a deep learning system was trained and evaluated. The training set included documents from hundreds of employees with more than 40 relevant data points. With an F1 score of 0.93, the resulting machine-based system achieved practically the same results as the reference values from humans (0.94) at a massively higher speed.

After these pleasing results, the service was made available to other employees via a smart web application. They can now initiate the readout process via an upload (API or via the web browser) and the processing steps (OCR, classification, extraction, normalisations) are carried out automatically. Via a graphical user interface, employees can visually carry out cross-checks and make any necessary adjustments. Afterward, the structured information is automatically transferred for credit analysis and a dossier is created and filed for each customer.

Key Features of the Acodis Platform

The Acodis platform comes with the following key features: 

State-of-the-art Technology Icon_Case Studies_Acodis
Automated Document Pipeline 

With OCR, data extraction & validation

Case Study_User Friendly
User-Friendly Labelling Tool


Easy to use and allows a fast labeling process

Manual Review Icon_Case Studies_Acodis
Display Of the Information Read Out

For quick visual inspection

Research Icon_Case Studie_Acodis
Inclusion of Confidence Values per Data Point


For accurate analyses

Case Study_Independent
Independent Control of Target Values


In order to automate and make adjustments

Benefits Solution_Documents
Automated Creation of Customer Dossiers & Customer Reports

To speed up internal processes

Benefits of Acodis IDP

Thanks to intelligent document processing (IDP), the customer benefits from the following added values, among others:

Future IDP Icon_Case Studies_Acodis

Increased Efficiency in the Sales Department

Services Icon_Case Study_Acodis
Further Digitalisation & Automation of the Business
Save Resources Icon_Case Study_Acodis
Process Standardisation & Harmonisation

Outcome

With Acodis IDP, the customer has a modern application for the automated capture of payroll data - anytime, anywhere. The solution is flexible and allows document analysis to be seamlessly integrated into existing processes and to include other use cases such as fraud detection.

Nothing Replaces a Conversation

We're looking forward to speaking with you.

CONTACT US