Connect with us

Hi, what are you looking for?


The race to digitization in logistics through machine learning

A recent Forbes article highlighted the importance of increasing digital transformation in logistics and argued that many tech leaders should be adopting “tech-forward thinking, execution and delivery” in order to deliver with speed and keep a laser focus on the customer.

Since the COVID-19 pandemic, and even before, many logistics companies have been turning to technology to streamline their processes. For many, full digitization across the supply chain is the ultimate goal.

Despite many already taking steps toward advancing digitization efforts across supply chains, these processes are still fragmented due to all the moving parts and sectors of the industry — such as integrators, forwarders and owners — and the processes they each use.

Scale AI is partnering with companies in the logistics industry to better automate processes across the board and eliminate bottlenecks by simplifying integration, commercial invoicing, document processing and more through machine learning (ML).

ML is a subfield of artificial intelligence that allows applications to predict outcomes without having to be specifically programmed to do so.

The logistics industry has historically depended on lots of paperwork and this continues to be a bottleneck today. Many companies already use technology like optical character recognition (OCR) or template-based intelligent document processing (IDP). Both of these are substandard systems that can process raw data but require human key entry or engineers to make the data usable through creating and maintaining templates. This is costly and cannot be scaled easily. In a world where the end users are moving to getting results instantly and at a high quality, these methods take too long while providing low accuracy.

“In the industry of logistics, it is a race to digitization to create a competitive edge,” said Melisa Tokmak, General Manager of Document AI at Scale. “Trying to use regular methods that require templates and heavily rely on manual key entry is not providing a good customer experience or accurate data quickly. This is making companies lose customer trust while missing out on the ROI machine learning can give them easily.”

Scale’s mission is to accelerate the development of artificial intelligence. 

Scale builds ML models and fine-tunes them for customers using a small sample of their documents. It’s this method that removes the need for templates and allows all documents to be processed accurately within seconds, without human intervention. Tokmak believes that the logistics industry needs this type of technology now more than ever.

“In the market right now, every consumer wants things faster, better and cheaper. It is essential for logistics companies to be able to serve the end user better, faster, and cheaper. That means meeting [the end users] where they are,” Tokmak said. “This change is already happening, so the question is how can you as a company do this faster than others so that you are early in building competitive edge?”

Rather than simply learning where on a document to find a field, Scale’s ML models are capable of understanding the layout, hierarchy and meaning of every field of the document.

Document AI is also flexible to layout changes, table boundaries and other irregularities compared to that of traditional template-based systems.

Tokmak believes that because the current technology of OCR and IDP are not be getting the results needed by companies in the industry, the next step is partnering with companies, like Scale, to incorporate ML into their processes. After adopting this technology, Tokmak added that this can lead to companies knowing more about the market and getting visibility on global trade, which can lead to building new relevant tech.

Flexport, a recognizable name in the logistics industry and customer of Scale AI, is what is referred to as a digital forwarder. Digital forwarders are companies that digitally help customers through the whole shipment process without owning anything themselves. They function as a tech platform to make global trade easy, looking end to end to bring both sides of the marketplace together and ship more easily. 

Before integrating an ML-solution, Flexport struggled to make more traditional means of data extraction like template-based and error-prone OCR work. Knowing its expertise was in logistics, Flexport partnered with Scale AI, an expert in ML, to reach its mission of making global trade easy and accessible for everyone more quickly, efficiently, and accurately. Now Flexport prides itself in its ability to process information more quickly and without human intervention.

As the supply chain crisis worsened, Flexport’s needs evolved. It became increasingly important for Flexport to extract estimated times of arrival (ETAs) to provide end users more visibility. Scale’s Document AI solution accommodated these changing requirements to extract additional fields in seconds and without templates from unstructured documents by retraining the ML models, providing more visibility on global trade at a time when many were struggling to get this level of insight at all. 

According to a recent case study, Flexport has more than 95% accuracy with no templates and a less than 60-second turnaround since partnering with Scale.

Tokmak believes that in the future, companies ideally should have technology that functions as a knowledge graph — a graph that represents things like objects, events, situations or concepts — and illustrates the relationship among them to make business decisions accurately and fast. As it pertains to the logistics industry, Tokmak defines it as a global trade knowledge graph, which would provide information on where things are coming and going and how things are working, sensors — all coming together to deliver users the best experience in the fastest way possible.

“Realistically this will take time to fully incorporate and will require partnership from the logistics companies. The trick to enabling this future is starting with what will bring the best ROI and what will help your company find the easiest way to build new cutting edge products immediately,” Tokmak said. “There is a lot ML can achieve in this area without being very hard to adopt. Document processing is one of them – a problem not solved with existing methods but can be solved with machine learning. It is a high value area with benefits of reducing costs, reducing delays, and bringing one source of truth for organizations within the company to operate with.”

Tokmak stated that many in the industry have been disappointed with previous methods and were afraid to switch to ML for the same fear of disappointment but that has changed quickly in the last a few years. Companies do understand ML is different and they need to get on this train fast to actualize the gains form the technology. 

“It is so important to show people the power of ML and how every industry is getting reshaped with ML,” Tokmak said. “The first adopters are the winners.”