Posti boosts purchase invoice processing with intelligent automation
Posti has elevated their RPA team to the next level by adding machine learning into their toolbox. Using Aito’s artificial intelligence together with software robotics has allowed Posti to work on intelligent automation independently from the data science team, and their first implementation now live in production, tirelessly churning digital purchase invoices every month.
Automation in the Finnish logistics giant
As the largest postal service operator in Finland, Posti delivers hundreds of thousands of parcels and envelopes daily around the country. This naturally involves much more behind the scenes than just the logistics though, and for this reason automation has been at the core of Posti for years.
To streamline its operations, Posti’s Intelligent Automation Team is automating numerous business processes within the company. Now with a generalist AI tool, the Intelligent Automation team can churn even complex processes without having to go through the normal data science pipeline.
Handling purchase invoices
By using Aito.ai in collaboration with Sisua Digital, Posti has automated their purchase invoice processing, which was formerly infeasible using traditional methods. Handling new invoices every month requires several cognitive decisions. Each digital invoice needs to be:
1. Assigned to the right reviewer
2. Allocated to the right cost center
3. Tagged for the right category
4. Corrected in case of missing information
Visualizing the problem with some mock data, this is how a new invoice looks like entering the system. A correct value needs to be selected for the empty fields.
The process is now automated with a software robot running on UiPath which interacts with Aito. The robot reads the information in each new invoice and asks Aito to predict the right values.
Launching the robot
The robot was operated in parallel with the manual process for one month and all the predictions of Aito were recorded for evaluation. During this simulation the predictions fulfilled the accuracy requirement of 95% set by the project steering group, giving it the green light for production. The first version of automation includes one legal company and a couple of types of purchase invoices. Later in the fall, more companies and invoice types will be added.
In the first stage of production, more than 7,000 purchase invoices have been processed thus far. Aito’s predictions have been at the expected level. The coverage and accuracy of tax class prediction has been close to 100%. Accounting and cost center coverages were good, ranging between 50-70% maintaining the allowed 5% error margin. The coverage of the invoice reviewer prediction was lower than expected, due to the substitutions during the summer holidays. Posti aims to increase volumes and raise the accuracy to over 80% in the coming months for all predictions.
The automation reduces the workload on the Accounts Payable team at Posti while boosting the speed of invoice review. As a result, the Accounts Payable team can now focus on more productive tasks. More importantly, the Posti RPA team now has the ability to replicate the technology for countless other business processes. After the initial learning curve, the RPA developers at Posti found Aito very straightforward to use together with the standard UiPath functionality.
Finland’s leading postal and logistics company, Posti, offers a wide range of postal, logistics, freight and e-commerce services. Posti has the most comprehensive service network in Finland and Posti deals with about three million households and companies on weekdays. The company employs approximately 21,000 people and operates in eight countries.
Benefits of the automation process:
- Posti now has the ability to replicate the technology to other business processes
- Manual, boring routine work has been removed from Posti’s employees
- Employees have more time for meaningful work
- Days of routine work has been saved
- Procedures and information have been harmonized
© 2020 Sisua Digital Oy All Rights Reserved