The views expressed here are solely those of the author and do not necessarily represent the views of FreightWaves or its affiliates.
In this installment of the AI in Supply Chain series (#AIinSupplyChain), we explore how Shipamax is helping logistics organizations around the world automate data entry, a critical but time-consuming activity.
Shipamax is based in London. It was founded in 2016 and was one of the startups in Y Combinator’s Winter 2017 (YC W17) cohort.
Solving the date entry dilemma
Jenna Brown is CEO and co-founder of Shipamax. I first met Brown in February 2017. In a recent interview, I asked her, “What is the problem that Shipamax solves for its customers? Who is the typical customer?”
“Shipamax delivers data entry automation across entire logistics organizations,” Brown said. “As an example of data entry automation, if you get sent a commercial invoice, Shipamax extracts that data and sends you a clean, structured data feed that can be imported to your transportation management system or enterprise resource planning system.”
She added, “In the commercial invoice case, these documents can be particularly problematic as there can be huge amounts of line items ops teams need to process before they can submit to customs. With the extra pressure of Brexit over here in the U.K., getting these processed quickly, at scale, is a huge challenge.”
“We see core themes in organizations when they buy Shipamax — scaling their operations more profitably, unlocking process improvements, and ensuring compliance across their global processes. Our typical customers are mid[size] and large freight forwarders across Europe, North America and Australasia,” she said.
Shipamax’s secret sauce
As is customary with the startups that serve as context for our exploration of #AIinSupplyChain, I asked Jenna, “What is the secret sauce that makes Shipamax successful? What is unique about your approach? Deep learning seems to be all the rage these days? Does Shipamax use a form of deep learning? Reinforcement learning? Supervised learning? Unsupervised learning? Federated learning? Natural language processing?”
She said, “Of course, technology is a key ingredient. We have a very experienced technology team for a ‘startup’ — our multiple, senior leads have 15 to 20-plus years experience, coming from institutions such as Google, Bloomberg and Facebook.”
She added that, “The vast majority of the data science team holds Ph.D.s and worked at leading research institutions. Our chief technology officer developed the first Chinese-English speech recognizer while at Nanyang Technological University, after studying at Karlsruhe and Carnegie Mellon under leading professors of machine learning.”
Getting more specific, she said, “Of course, Shipamax uses a number of techniques including deep learning, supervised learning, active learning and natural language processing. Active learning is interesting as it enables us to incorporate feedback from end users to improve data extraction. We combine a number of different algorithms depending on the problem at hand and build our own algorithms in house.”
Regular readers of this column will recall that in this #AIinSupplyChain series, we first encountered supervised learning and unsupervised learning in Commentary: AI, machine learning generate insights on global ag for Gro Intelligence. We first encountered NLP in Commentary: SEDNA Systems improves how teams work worldwide.
According to Algorithmia, “Active learning is the subset of machine learning in which a learning algorithm can query a user interactively to label data with the desired outputs. In active learning, the algorithm proactively selects the subset of examples to be labeled next from the pool of unlabeled data.”
Active learning attempts to reconcile the need for accuracy with the requirement for large data sets by placing a human expert in the machine learning loop to reduce the amount of data required by the machine learning algorithms, while increasing accuracy.
Active learning is a form of supervised learning.
Emphasizing that there’s more to come from Shipamax on this front, Brown said, “There are six core components of our secret sauce — these are the things that supercharge accuracy. We’ll be publishing more on these soon! We call this our ‘Contextual Understanding Layer.’”
Customers and competition
I asked Brown if there are any customers Shipamax is free to speak about.
“We’re just about to go public with a whole batch!” she said. “One company I think is really interesting is Seaway. They’ve successfully rolled out two of our solutions and will be the first beta client on one of our new launches — Commercial Invoices for Customs data entry.”
In an October announcement that Seaway had selected Shipamax’s Document Data Capture Solution, Adrian Green, head of business improvement at Seaway, said, “The technology used by Shipamax is superior to anything that we have tried in the past. … The solution is already having a positive impact on our operations team. Data capture was once a time consuming and expensive task managed by multiple operators, but with Shipamax, it has evolved into a fully automated process, allowing operators to spend less time on data entry and more time focused on valuable customer-facing tasks.”
Seaway is a diversified transportation and logistics services company based in Australia. It has been in business since 1999.
Before Shipamax, customers typically relied on optical character recognition technology. OCR is used to capture and extract information from documents and then convert that information into machine-readable formats.
What’s next for Shipamax?
Shipamax had a strong start to 2020. Things hit a speed bump in March and April as the COVID-19 pandemic unfolded and potential customers paused to adjust their companies to work from home. Business regained momentum during the second quarter of 2020 because Shipamax’s product lends itself to the work-from-home environment to which potential customers needed to readjust.
The team at Shipamax has learned to focus on solving customers’ problems rather than on being enamored with the technology they are building. As a result, Brown expects that they will focus on enhancing the scalability and repeatability of the internal processes at Shipamax, with an emphasis on customer success and sales.
According to Brown, there are three key trends motivating potential customers to start looking at automation: First, Brexit is increasing the compliance and regulatory documentation burdens on companies in the U.K. Second, Amazon has raised the bar for customer experience in retail. Other retailers are turning to their freight forwarders for help, and in turn the freight forwarders are seeking technology innovations from startups like Shipamax. Third, the rise in relatively small e-commerce, direct-to-consumer businesses is prompting traditional freight forwarders to seek technology to enable them to offer their services to this new category of customers.
Taken together, the developments in 2020 have led the team at Shipamax to believe that 2021 will be a year in which the startup starts scaling growth.
If you are a team working on innovations that you believe have the potential to significantly refashion global supply chains, we’d love to tell your story in FreightWaves. I am easy to reach on LinkedIn and Twitter. Alternatively, you can reach out to any member of the editorial team at FreightWaves at media@freightwaves.com.
Dig deeper into the #AIinSupplyChain Series with FreightWaves.
● Commentary: Optimal Dynamics – the decision layer of logistics? (July 7)
● Commentary: Combine optimization, machine learning and simulation to move freight (July 17)
● Commentary: SmartHop brings AI to owner-operators and brokers (July 22)
● Commentary: Optimizing a truck fleet using artificial intelligence (July 28)
● Commentary: FleetOps tries to solve data fragmentation issues in trucking (Aug. 5)
● Commentary: Bulgaria’s Transmetrics uses augmented intelligence to help customers (Aug. 11)
● Commentary: Applying AI to decision-making in shipping and commodities markets (Aug. 27)
● Commentary: The enabling technologies for the factories of the future (Sept. 3)
● Commentary: The enabling technologies for the networks of the future (Sept. 10)
● Commentary: Understanding the data issues that slow adoption of industrial AI (Sept. 16)
● Commentary: How AI and machine learning improve supply chain visibility, shipping insurance (Sept. 24)
● Commentary: Can AI and machine learning improve the economy? (Oct. 8)
● Commentary: Savitude and StyleSage leverage AI, machine learning in fashion retail (Oct. 15)
● Commentary: How Japan’s ABEJA helps large companies operationalize AI, machine learning (Oct. 26)
● Commentary: Pathmind applies AI, machine learning to industrial operations (Nov. 20)
● Commentary: Chain of Demand applies AI, machine learning to retail supply chain profitability (Nov. 26)
● Commentary: AI, machine learning generate insights on global ag for Gro Intelligence (Dec. 10)
● Commentary: SEDNA Systems improves how teams work worldwide (Dec. 19)
Author’s Disclosure: I am not an investor in any early-stage startups mentioned in this article, either personally or through REFASHIOND Ventures. I have no other financial relationship with any entities mentioned in this article.