The Business Problem

In this business case, AI workflow automation will be exemplified using the example of a TradeCloud client. The client is a manufacturer of machines for the sorting of eggs and is based in the Netherlands. The company has more than 200 suppliers for its components, which means putting a lot of focus on error-reduction and efficiency improvements.

There are various factors that can disrupt a good running workflow. First, supplier reliability is a big concern. How often does a supplier deliver the right quantity, at the right time and at the right place?

The second challenge, administrative tasks. A lot of manual work has to be done to process the incoming and outgoing orders. The machine manufacturer has over 85.000 order lines per year that need to be sent to suppliers, meaning an equal number of confirmations need to be made and checked. Only a small proportion will involve changes, but to manually check each line takes up a lot of time. Time that customers are not willing to pay for.

The third challenge, visibility of order history. To see what is arriving at what time and what possible exceptions there could be, the supply chain manager needs to constantly check if everything is going well.

The fourth challenge is flexibility. How flexible can a supplier be? Is it possible to deliver 20 items less or more? how quickly? and at what costs? These challenges are further compounded by ever-shorter lead times, in-house standardization and client customization.

The Solution

AI based exception handling and risk analysis with TradeCloud One

TradeCloud’s AI solution is specifically targeted at exception handling. The solution automates the entire process of sending and receiving orders to suppliers. As soon as a purchase order is created in an ERP system, it is automatically sent to the supplier, saving manual work. If the supplier confirms exactly what was asked for, the client doesn’t have to look at it anymore – everything that matches to the needs of both the supplier and customer is automatically processed.

What’s left are the exceptions: this is where the AI solutions come in. For the machine manufacturer, about 90% of the orders are automatically accepted while 10% have one or more exceptions. These exceptions could be an item being delivered a day or a week later, not in stock, price changes, etc. The AI application checks the exceptions and cross-references them with historical data to decide whether this exception is a problem or not.

Example

A supplier confirms an order to be delivered one week later than planned. Traditionally, the order has to be checked manually to confirm or reject this exception. TradeCloud’s AI solution looks at stock levels of this item on the date that the supplier proposed to deliver. It then analyses whether this will be a problem or not. When there is enough stock at that time, and there are no orders that need that item, then the order will be accepted. The AI automatically approves this exception.

The second AI solution is risk analysis. It involves TradeClouds’s self-learning AI model, based on historical data and order line exceptions. The AI solution predicts, on an order line level, whether there is a potential risk exception for this order. The solution works like a traffic light: red, orange or green. If the item never had any exceptions in the past, the probability of on-time deliveries will result in a ‘green’ light. If an exception was encountered in the past, or external factors might influence the order – such as out-of-the-ordinary weather in the region of the supplier, or general supply chain bottlenecks – it results in an ‘ orange’  or even ‘ red’  light, based on severity.

Benefits & Impact

The key benefits of the AI solution are better automated tasks, higher supplier reliability and more time for focusing on optimization. Automatic order handling with AI saves time for employees doing repetitive, non-value adding tasks, such as confirming (unchanged) orders, checking order status and sending documents.

Secondly, supplier reliability can be significantly increased with automated workflow handling. Clients can reduce safety stock, thus also reducing costs. Thirdly, purchasers can now work on adding value and optimisation, instead of reading through data. Leading clients to start focusing more on creating adding value for its own clients.

The impact of an automated workflow for the machine manufacturer was:

  • Supplier reliability was increased from 82 to 97%, a 15% increase.
  • 50% time saved on employees doing ‘dumb work’
  • A saving of 2 FTE’s, meaning €150.000 euros in direct savings
  • Approximatively €500.000 in indirect savings, since the company had to carry less stock, there were less mistakes by employees and there was less risk. This could be even higher, up to 1,5 million euros in indirect savings, due to more reliable production processes. A happy factory flow means less errors.
  • A return of investment (ROI) in 12 months. The AI solution is bringing 10 times more value than it costs.

Accessibility and Requirements

To make use of TradeCloud’s AI solutions, several things are necessary. Of course, a company has to have their own systems up and running. But most importantly, a plan for collaboration within the TradeCloud environment with suppliers has to be created. An incentive to join TradeCloud might be appropriate for suppliers. For example: Payments to the supplier could be done earlier.

The results of this AI solution can be reached within several months. The implementation is about getting the application up and running. For proof of concept, a client might start with one supplier, before expanding to the rest of the suppliers.

Necessary data for TradeCloud’s AI solutions to build and train the model could include:

  • Stock levels
  • Order history
  • Purchase order history
  • Item
  • Date
  • Price
  • Confirmation history – what was confirmed by the suppliers
  • Delivery history – what was delivered in the end

In the near future, TradeCloud’s AI solution will be using external data to make better predictions for exception handling. The order could be impacted by many external factors, for example bad weather, a delayed airplane, supplier bankruptcy, manufacturing problems or a boat stuck in the Suez Canal. By implementing these external factors to the existing datasets, the accuracy of the predictions will improve. Resulting in even better results regarding supplier reliability and cost-saving.

Want to know more what AI can do for your supply chain?
Contact us.

More AI Case Studies:

AI case study 3: Cost-saving AI in Manufacturing Logistics

The Business Problem In the world of logistics, empty fleet management cannot be overlooked. For container shipping, the Boston Consulting Group estimates that up to 8% of a shipping line's operating costs relate [...]

AI case study 1: Demand Forecasting using Artificial Intelligence

The Business Problem One of the biggest challenges for business executives today is demand volatility in relation to demand forecasting. Whereas data availability continues to increase, customer purchase patterns are becoming increasingly complex, and [...]

Bibliography

Alexsoft. (2019, November 11). Demand Forecasting Methods: Using Machine Learning and Predictive Analytics to See the Future of Sales. Retrieved April 6, 2021, from Alexsoft

Armstrong, M. M. (2020, December 4). Cheat sheet: What is Digital Twin? Retrieved April 21, 2021, from ibm.com

BCG. (2015, November 17). Think Outside Your Boxes: Solving the Global Container-Repositioning Puzzle . Retrieved from Boston Consulting Group

Best Practice AI. (n.d.). Danone reduces forecast error and lost sales by 20 and 30 percent respectively and achieve a 10 point ROI improvement in promotions with machine learning. Retrieved April 6, 2021, from Bestpractice

Brosset, P., Patsko, S., Khadikar, A., Thieullent, A., Buvat, J., Khemka, Y., & Jain, A. (n.d.). Scaling AI in Manufacturing Operations. Retrieved April 06, 2021, from Capgemini

Caulfield, B. (2019, December 16). What’s the Difference Between a CPU and a GPU? Retrieved April 22, 2021, from nvidia.com

Dilmegani, C. (2021, January 7). Demand forecasting in the age of AI & machine learning [2021]. Retrieved April 6, 2021, from AImultiple

Europawire. (2020, April 15). Shipment planning and inventory management improved with AI and big data on Kuehne + Nagel’s new version of SeaExplorer. Retrieved from Europawire

Hyeongchan, K. (2020, December 16). Detecting Sounds with Deep Learning. Retrieved April 21, 2021, from towardsdatascience.com

Kvartalnyi, N. (2021, May 11). 6 TIPS OF HOW TO IMPROVE INVENTORY MANAGEMENT USING ARTIFICIAL INTELLIGENCE. Retrieved from Inoxoft

Majumdar, D. (n.d.). Case Study-How SynergyLabs AI solutions Brought Efficiency in warehouse Inventory management. Retrieved April 19, 2021, from Synlabs

Micron Technology. (2021). Case Study: Micron Uses Data and Artificial Intelligence to See, Hear and Feel. Retrieved April 21, 2021, from sg.micron.com

Opperman, A. (2019, November 19). What is Deep Learning and How does it work? Retrieved April 21, 2021, from towardsdatascience.com

Serheichuk, N. (2020, December 15). Inventory management automation: How you can benefit from it. Retrieved from N-ix

Subramanyam, J. (2019, July 8). Prediction Models: Traditional versus Machine Learning. Retrieved May 20, 2021, from Gartner.com

Supply Chain 247. (2017, March 28). Coca-Cola Leverages AI for Inventory Management. Retrieved from SupplyChain247

Supply Chain Dive. (2018, August 17). Two-thirds of companies consider Excel a supply chain system. Retrieved from Supply Chain Dive

Symphony Retail. (n.d.). demand forecasting ai. Retrieved April 06, 2021, from symphonyretail

TradeGecko. (2019, December 4). What is inventory management? Retrieved from tradegecko

Tuv, E., Murat, G., Enis, P., & Lee, D. H. (2018, November). Faster, More Accurate Defect Classification Using Machine Vision. Retrieved April 21, 2021, from Intel.com