CUSTOMER CASE | RETAIL SECTOR
Kekäle utilizes machine learning in invoice processing
Share
The Finnish clothing store Kekäle has grown its business rapidly, which brought on the need to accelerate processing the company’s purchase invoices. To reduce the increased manual workload, Kekäle chose an intelligent automation solution built by Sisua Digital. The automation solution has eliminated 85% of the manual work associated with the process and improved the quality of the process.
The strong growth of Kekäle and the expansion of their stores increased the number of invoices processed in their financial administration. In addition, Kekäle’s financial administration had begun to allocate expenses more precisely. Due to the growth and the new allocation, the manual workload in processing purchase invoices had increased significantly. The invoice management system used by the company had also not met Kekäle’s individual needs. They wanted to streamline the purchase invoice processing, and the solution developed for that was intelligent automation that utilizes machine learning.
The robot implemented by Sisua Digital reads the invoices entered in the invoice management system and determines where the invoices are directed. Some of the invoices are sent to the system electronically and some as paper, which the invoice management system scans into pdf files. These pdf files are recognized by the robot from image to text format using machine learning, or OCR (Optical Character Recognition) technology.
Machine learning has also been used in allocating invoices: when the automation was created, test invoices were collected, on the basis of which a set of rules was created. Based on these rules, the robot is able to prove the invoices to be correct.
The intelligent automation solution processes the majority of invoices, improves the process accuracy and patches invoice system deficiencies
Developed as a virtual assistant for the financial administration department, the robot now handles most of the purchase invoices that were previously processed manually.
The accuracy that the robot entails also increases the reliability of the process. The robot checks for things that might go unnoticed by humans and reports if something is wrong. The robot also patched the shortcomings of the invoice management system: it corrects errors in the interpretation of the system and has created special rules for certain suppliers. This way the automation meets Kekäle’s individual needs better.
The robot processes daily invoices in about an hour, when it used to take about three hours before the automation. The robot also balances the workload during peak periods caused by seasonal variations. At the same time, the robot reports about the number of invoices, which allows for proactive planning.
The automation was implemented within three weeks from starting to design the project
The development of the project was agile and the automation was quickly brought into production. The robot started processing invoices within three weeks from starting to plan the project. Since then, the process has been iteratively developed during continuous service.
“The implementation of the service went very smoothly. We have developed the service better all the time according to our needs and it is easy to follow the robot's work. Most invoices now go forward automatically and do not require manual processing. This has freed up a lot of working time from monotonous storing of invoices to other more meaningful tasks” states Elisa Huotari, from Kekäle's Financial Administration.
Sisua’s service platform for Kekäle enables process automation to be seamlessly extended to new automation targets, such as order processing and inventory management.
Author: Paiju Koivula
What was achieved
Automation benefits

- Manual workload was reduced by 85%
- Time was freed up for more meaningful tasks
- Improved process accuracy
- Reduced number of errors
- Flaws of the invoicing system were patched
- Workload during peak season is alleviated
- The automation improves statistics
About the company
Kekäle
Kekäle is a Finnish clothing store founded in 1957, which employs more than 140 people. The company has 11 stores nationwide as well as an online store, from which it serves more than 200,000 customers annually. The dynamic growth company focuses on quality and durable clothing instead of fast fashion. Digitalization is seen as an endeavor that supports the entire store network in the company.
Book a free consultation with us
Want to know how intelligent automation could benefit your company? Tell us about your automation needs and let’s find the right solution for your company together.