Transalis uses AI to transform SMEG’s order processing

Narrow AI, a term used to describe artificial intelligence systems that are focused on handling a particular or limited task, is steadily finding its way into mainstream industry applications for the benefit of companies and their suppliers, distributors and customers.

A prime example is the automation of order processing, an essential back-office discipline to ensure trading partners engage easily and cost-effectively.

One common barrier to efficient working is that different partners will typically diverge in how they present order information. While bigger suppliers and customers may well operate structured document systems based on EDI, or electronic data interchange, others will not. They are likely to be sending order information on PDFs or in spreadsheets, which has been keyed in manually and needs to be extracted manually too.

This is where the scope for human error comes in. There can easily be ‘typos’ that make product codes or postal addresses ambiguous, something that needs the eyes of an administrator to resolve. For example, the letter ‘O’ can be confused with ‘0’ for zero, or the letter ‘S’ can be mistaken for the number ‘5’.

Manual checking and correction may be feasible where the distribution network or customer base is small, but not in any sizeable business operation with multiple transactions going on at any given time.

Learning from last time

In response, digital trading specialist Transalis has developed a solution to apply learnings and to correct and ‘repair’ invalid data on new orders. Of course, the solution also allows the repairing of data in structured documents, for example where there was an error in an ordering system in the first place – perhaps a wrong or outdated product code.

In the case of a corrected postcode, the system can even collaborate with third parties such as Royal Mail to validate a postcode, once repaired.

This gives companies and organisations the prospect of greater competitive advantage by dramatically reducing error rates which otherwise take time and budget to sort out.

One of the first users is the UK subsidiary of leading domestic, industrial and laboratory appliance manufacturer SMEG. Hundreds of orders each week are received from across their UK distribution network, including from retailers, distributors and resellers. Most issues needing to be addressed have tended to surface within a couple of weeks of starting with a new customer.

Channelled through Transalis’ cloud-based paper-to-digital data interchange platform, the orders needing correction are typically PDF attachments received by email.

Because of the extent of the network and the many different systems and protocols of distributors, Transalis is using Narrow AI technology to standardise the order information that is interpreted, extracted and presented to SMEG.

Teaching the system

Accuracy means the particular item can be easily found if it’s in stock. Any mistake, for example in the item reference number or product code, immediately hampers this task as checks will take more time and effort to complete, requiring additional calls and emails between SMEG and the trading partner. This can lead to additional costs and delayed deliveries.

To solve this, Transalis has re-engineered the traditional data capture process to ‘teach’ the system what it needs to fix including typos involving item numbers and characters.

The solution essentially ‘feeds’ the system with knowledge of how the particular issue was solved before. This enables the error to be auto-corrected if it happens again. The same approach to reuse and validation is also automatically applied to new customers coming on board.

Cerie Paton, Head of Business Systems at SMEG (UK), says: “As the solution begins to process the data, it identifies any duplication or validation problems. If an error is picked up, the system immediately notifies the Transalis technical support team to take action. Once a correction is made, it will be resolved automatically the next time the same error is shown. The data flows handled by Transalis are updated by a weekly list generated here at SMEG which is populated with any new products and orders.”

Reducing errors

The Transalis solution has significantly reduced inbound order error rates from around 15% to well below half a percent.

Cerie says the Transalis solution has produced demonstrable ROI.

“We had been working with Transalis on various aspects of order processing and knew that some of our customers and trading partners just don’t integrate with EDI. The data we need from them is not sent in a digital format – it’s unstructured, it can have errors in it, and it takes time to sort out.

“We asked Transalis to find us a solution for automating, integrating and validating the data we were receiving. After we explained our issues and concerns, they built, tested and put live an API within ten days or so. They worked with us to understand where any issues were coming from, why any data was failing, and how mistakes could be resolved. They have the development and technical support skills to overcome data accuracy issues.

“We are very happy with their solution. It has given us complete confidence that order processing is accurate and essentially error-free. The two main benefits are that we can now easily integrate orders from different customers who are not using structured digital data or EDI, and we have information from retrieved text files that is accurate. Transalis has resolved integration needs and removed data management headaches.”

As the experience of SMEG UK indicates, Transalis’ solution can ensure the flow of information between a company and its trading network is smoother and more cost-efficient, with consequent benefits in both time and cost savings.

Summary of Benefits

• Competitive advantage
• Dramatic reduction in error rates
• Automated validation
• Applies automatically to new orders and customers
• Smoother, more cost-efficient data flows
• Demonstrable return on investment
• Confidence in order processing accuracy
• Removal of data management headaches

Stavros Michael is Development Manager for Customer Projects at Transalis.

You may also be interested in:

What is eDI?

The benefits of eDI

How much can I save with eDI?