May 17, 2020

Machine learning: innovative technology within supply chains

Supply Chain
Technology
Georgia Wilson
6 min
Supply Chain Digital takes a look at machine learning services available and how they are being adopted within supply chains
Watson is IBM’s suite of artificial intelligence (AI) services, applications and tools. Watson aims to help businesses unlock the value of data in new...

Watson is IBM’s suite of artificial intelligence (AI) services, applications and tools. Watson aims to help businesses unlock the value of data in new ways and remove repetitive tasks from employees to shift the focus to high-value work. This is in addition to allowing companies to predict and shape business outcomes in order to rethink practices and workflow.

A part of IBM Watson’s AI services is machine learning. Watson’s software has been developed to help data scientists and developers integrate AI into company applications. Watson Machine Learning enables cross-functional teams to deploy, monitor and optimise models quickly and easily. 

BASF: Building a smart supply chain

BASF Nutrition and Health – a division of chemical group BASF – partnered with IBM in early 2019 as part of its wider vision to make digitalisation an integral part of the business.

BASF requires high delivery performance for its products with end-to-end coordination across suppliers, manufacturers, logistics partners and distribution centres as well as the ability to manage dysfunctional inventory. Partnering with IBM, BASF explored how AI and machine learning could create smarter inventory decisions and ensure products arrive in the right place at the right time.

With the help of IBM Watson’s cognitive intelligence BASF and IBM first built a proof of concept (PoC) to evaluate how AI and machine learning could be utilised to build a more powerful Replenishment Advisor tool. Following the evaluation, IBM Watson and BASF designed a model based on transactional order data and future orders from the company’s ERP system as well as sales pattern reports, volume strategy, inventory levels and shipping times. Using open-source machine learning a custom solution was built to predict future replenishment requirements.

After completing just 10 training cycles the software provided accurate, early warnings for stock replenishment and the optimal time for minimal disruption.

“IBM Cloud and Watson AI services gave us access to a wide range of machine learning models with IBM experience built in, right out of the box,” said Dr. Bernd Lohe, Director Supply Chain Operational Excellence & Digitization at BASF Nutrition & Health. “This meant that we could start analysing our data and training the Replenishment Advisor immediately. The solution also includes data visualizations. During the training phase, this helped our planners to understand system recommendations and to execute effective training loops for machine learning. An integrated chatbot functionality is built into the Replenishment Advisor, allowing staff to interact with the solution using natural language. Based on our successful PoC, we are very satisfied with the IBM Watson portfolio, both in terms of the powerful cognitive capabilities and ease of use.”


KIST Europe: Making factories smarter

KIST Europe – the first overseas branch of Korea Institute of Science and Technology (KIST) – aims to build open innovation platforms for leading Korean and European research institutes and industry partners. One of KIST’s key research areas is the concept of ‘Industry 4.0’, the evolution of technology from centralised systems governed by human intelligence to decentralised machines that can operate independently.

To test and demonstrate the value ‘Industry 4.0’ can add to the manufacturing industry, KIST Europe partnered with SmartFactory and IBM Watson to improve weight measurements, an integral part of quality management. “The technology behind SmartFactory is impressive, but manufacturers are not interested in technology for its own sake. To prove the value of the ‘Industry 4.0’ approach, we need to show how the factory can solve real-world manufacturing problems,” said Marco Hüster, Business Lead AI Implementation at KIST Europe.

In manufacturing, the smallest deviation from the expected weight can signify a fault in either the component, product or production line machinery. As a result, the three companies combined existing SmartFactory technology, data science solutions and a data set of 1,000 real world measurements with machine learning technology to produce a model that can now predict with 98.1% reliable measurement accuracy.

“Weight measurement is a very simple example, but it proves that integrating AI and smart factory technology can have a genuine impact on production-line efficiency and quality management,” commented Dr. Jongwoon Hwang, Group Leader, KIST Europe. “With IBM’s help, we are showing the industry how decentralized AI can help to deliver greater flexibility, optimize process management and predict the performance of production resources. As we continue to move towards a fourth industrial revolution, these capabilities will help pioneering manufacturers transform the industry and create new value for themselves and their customers.”

Amazon

Amazon Web Services (AWS) is Amazon’s comprehensive cloud platform for businesses. A service of AWS is Machine Learning, where customers have the ability to build, train and deploy models, apply and integrated pre-trained AI applications such as recommendations and forecasting, utilise flexible frameworks for custom algorithms and broad compute options as well as harness deep learning technology, analytics and security.

Convoy: Efficiency and the environment

In recent months, Convoy partnered with AWS to utilise its machine learning services developing a solution to make trucking more efficient and environmentally friendly.

40% of miles per year logged by truck drivers are completed with empty trucks. A part of the problem is the industry infrastructure combined with the use of traditional methods. Using AI Convoy looked to automate the process with the help of AWS.

By utilising Amazon SageMaker, Convoy developed a machine learning model that can analyse millions of shipping jobs and trucker availability, resulting in recommended matches that are cost and time efficient. In addition to this, the model will also recommend matches for the journey back, which reduces the number of miles completed by empty trucks, which in turn will have a positive impact on the environment.

“As we work with more shippers and carriers, we get a better understanding of how much capacity is available and how much demand is coming in on specific lanes,” says Casey Olives, Head of Data Science at Convoy. “Being able to have a contextual view of the entire network will enable us to drive efficiencies in utilisation and costs, benefiting both carriers and shippers.”

TuSimple: Autonomous Trucks

TuSimple, one of the world’s largest self-driving truck companies, has partnered with AWS to develop autonomous vehicles. Built primarily using the Apache MXNet deep learning framework on AWS, TuSimple vehicles have built in servers loaded with up to 100 different AI modules. These modules distinguish the types of cars on the road and the speed of other objects around the truck providing a steady stream of data from cameras, LiDAR, and radar equipment to build a live 3D model of the road that is constantly updated as the truck moves. After completing a successful delivery, the results are updated to the modules on every trucks server after completing safety test and simulations to ensure it will behave as expected. With the help of AWS’s massive computing power, this process takes hours rather than weeks.

Currently TuSimple’s trucks are at a ‘level 4’ autonomous vehicle classification and have a 5cm accuracy at 65 mph with a loaded trailer. By 2020, Xiaodi Hou, president and CTO of TuSimple, wants to remove human ‘fail-safes’ from the vehicles.

With firms worldwide at the beginning of an exciting future in the leveraging of new technology in the supply chain space, machine learning is set to feature even more prominently in company’s operations over the coming years.

For more information on all topics for Procurement, Supply Chain & Logistics - please take a look at the latest edition of Supply Chain Digital magazine.

Follow us on LinkedIn and Twitter.

Share article

Jun 11, 2021

NTT DATA Services, Remodelling Supply Chains for Resilience

NTTDATA
supplychain
Supplychainriskmanagement
Procurement
6 min
Joey Dean, Managing Director of healthcare consulting at NTT DATA Services, shares remodelling strategies for more resilient supply chains

Joey Dean, the man with the coolest name ever and Managing Director in the healthcare consulting practice for NTT DATA and is focused on delivering workplace transformation and enabling the future workforce for healthcare providers. Dean also leads client innovation programs to enhance service delivery and business outcomes for clients.

The pandemic has shifted priorities and created opportunities to do things differently, and companies are now looking to build more resilient supply chains, none needed more urgently than those within the healthcare system. Dean shares with us how he feels they can get there.

A Multi-Vendor Sourcing Approach

“Healthcare systems cannot afford delays in the supply chain when there are lives at stake. Healthcare procurement teams are looking at multi-vendor sourcing strategies, stockpiling more inventory, and ways to use data and AI to have a predictive view into the future and drive greater efficiency.

“The priority should be to shore up procurement channels and re-evaluate inventory management norms, i.e. stockpiling for assurance. Health systems should take the opportunity to renegotiate with their current vendors and broaden the supplier channel. Through those efforts, work with suppliers that have greater geographic diversity and transparency around manufacturing data, process, and continuity plans,” says Dean.

But here ensues the never-ending battle of domestic vs global supply chains. As I see it, domestic sourcing limits the high-risk exposure related to offshore sourcing— Canada’s issue with importing the vaccine is a good example of that. So, of course, I had to ask, for lifesaving products, is building domestic capabilities an option that is being considered?

“Domestic supply chains are sparse or have a high dependence on overseas centres for parts and raw materials. There are measures being discussed from a legislative perspective to drive more domestic sourcing, and there will need to be a concerted effort by Western countries through a mix of investments and financial incentives,” Dean explains.

Wielding Big Tech for Better Outcomes

So, that’s a long way off. In the meantime, leveraging technology is another way to mitigate the risks that lie within global supply chains while decreasing costs and improving quality. Dean expands on the potential of blockchain and AI in the industry

“Blockchain is particularly interesting in creating more transparency and visibility across all supply chain activities. Organisations can create a decentralised record of all transactions to track assets from production to delivery or use by end-user. This increased supply chain transparency provides more visibility to both buyers and suppliers to resolve disputes and build more trusting relationships. Another benefit is that the validation of data is more efficient to prioritise time on the delivery of goods and services to reduce cost and improve quality. 

“Artificial Intelligence and Machine Learning (AI/ML) is another area where there’s incredible value in processing massive amounts of data to aggregate and normalise the data to produce proactive recommendations on actions to improve the speed and cost-efficiency of the supply chain.”

Evolving Procurement Models 

From asking more of suppliers to beefing up stocks, Dean believes procurement models should be remodelled to favour resilience, mitigate risk and ensure the needs of the customer are kept in view. 

“The bottom line is that healthcare systems are expecting more from their suppliers. While transactional approaches focused solely on price and transactions have been the norm, collaborative relationships, where the buyer and supplier establish mutual objectives and outcomes, drives a trusting and transparent relationship. Healthcare systems are also looking to multi-vendor strategies to mitigate risk, so it is imperative for suppliers to stand out and embrace evolving procurement models.

“Healthcare systems are looking at partners that can establish domestic centres for supplies to mitigate the risks of having ‘all of their eggs’ in overseas locations. Suppliers should look to perform a strategic evaluation review that includes a distribution network analysis and distribution footprint review to understand cost, service, flexibility, and risks. Included in that strategy should be a “voice of the customer” assessment to understand current pain points and needs of customers.”

“Healthcare supply chain leaders are re-evaluating the Just In Time (JIT) model with supplies delivered on a regular basis. The approach does not require an investment in infrastructure but leaves organisations open to risk of disruption. Having domestic centres and warehousing from suppliers gives healthcare systems the ability to have inventory on hand without having to invest in their own infrastructure. Also, in the spirit of transparency, having predictive views into inventory levels can help enable better decision making from both sides.”

But, again, I had to ask, what about the risks and associated costs that come with higher inventory levels, such as expired product if there isn’t fast enough turnover, tying up cash flow, warehousing and inventory management costs?

“In the current supply chain environment, it is advisable for buyers to carry an in-house inventory on a just-in-time basis, while suppliers take a just-in-case approach, preserving capacity for surges, retaining safety stock, and building rapid replenishment channels for restock. But the risk of expired product is very real. This could be curbed with better data intelligence and improved technology that could forecast surges and predictively automate future supply needs. In this way, ordering would be more data-driven and rationalised to align with anticipated surges. Further adoption of data and intelligence and will be crucial for modernised buying in the new normal.

The Challenges

These are tough tasks, so I asked Dean to speak to some of the challenges. Luckily, he’s a patient guy with a lot to say.

On managing stakeholders and ensuring alignment on priorities and objectives, Dean says, “In order for managing stakeholders to stay aligned on priorities, they’ll need more transparency and collaborative win-win business relationships in which both healthcare systems and medical device manufacturers are equally committed to each other’s success. On the healthcare side, they need to understand where parts and products are manufactured to perform more predictive data and analytics for forecasting and planning efforts. And the manufacturers should offer more data transparency which will result in better planning and forecasting to navigate the ebbs and flows and enable better decision-making by healthcare systems.

Due to the sensitive nature of the information being requested, the effort to increase visibility is typically met with a lot of reluctance and push back. Dean essentially puts the onus back on suppliers to get with the times. “Traditionally, the relationships between buyers and suppliers are transactional, based only on the transaction between the two parties: what is the supplier providing, at what cost, and for what length of time. The relationship begins and ends there. The tide is shifting, and buyers expect more from their suppliers, especially given what the pandemic exposed around the fragility of the supply chain. The suppliers that get ahead of this will not only reap the benefits of improved relationships, but they will be able to take action on insights derived from greater visibility to manage risks more effectively.”

He offers a final tip. “A first step in enabling a supply chain data exchange is to make sure partners and buyers are aware of the conditions throughout the supply chain based on real-time data to enable predictive views into delays and disruptions. With well understand data sets, both parties can respond more effectively and work together when disruptions occur.”

As for where supply chain is heading, Dean says, “Moving forward, we’ll continue to see a shift toward Robotic Process Automation (RPA), Artificial Intelligence (AI), and advanced analytics to optimise the supply chain. The pandemic, as it has done in many other industries, will accelerate the move to digital, with the benefits of improving efficiency, visibility, and error rate. AI can consume enormous amounts of data to drive real-time pattern detection and mitigate risk from global disruptive events.”

 

Share article