The Business Problem

A major challenge for manufacturing companies is to know what, when, where and how much stock should be ordered and kept. SME’s traditionally calculate this manually using Excel, Google Sheets or other software solutions. These solutions can be automated to an extent and are fairly adequate in most cases. However, these traditional solutions are subject to human error and are based on the capabilities of the employee. As a result, human error can lead to wrong estimates and over/understock.

The Solution

AI-powered inventory management can provide a solution to human error by letting the computer do the math (TradeGecko, 2019). But how could an AI application make the inventory management process more efficient?

Determining the right amount of stock, in the right place, at the right time at the right costs as well as the right price. That is what inventory management is about in business terms and could be determined automatically by the AI application. This is done by combining datasets, developing a Machine Learning model and continuously training the model to achieve higher levels of accuracy over time. The outputs of the model reflect the most optimal decisions that can be taken.

Example

Coca Cola uses artificial intelligence for the inventory management of their cabinet coolers in retail outlets. The AI tool has been trained to recognize, identify and count the different Coca Cola products in the coolers.

The tool could combine this data with information received from demand forecasting (link to Rob’s business case), and automatically calculate an order to restock. Consequently, the retailer is offered a delivery choice. Additional information is also given on predicted demand for a cooler, with the aim of providing additional service and increasing Coca Cola’s sales (Supply Chain 247, 2017).

Benefits

Coca Cola uses artificial intelligence for the inventory management of their cabinet coolers in retail outlets. The AI tool has been trained to recognize, identify and count the different Coca Cola products in the coolers.

The tool could combine this data with information received from demand forecasting (link to Rob’s business case), and automatically calculate an order to restock. Consequently, the retailer is offered a delivery choice. Additional information is also given on predicted demand for a cooler, with the aim of providing additional service and increasing Coca Cola’s sales (Supply Chain 247, 2017).

Several key benefits for the use of AI in inventory management are:

  • Saving time and money: by automating inventory management with AI, it is possible to save manual labour and thus money. Businesses can save between $6,000 and $72,000 depending on their inventory size.
  • Increasing scalability: automated inventory management allows companies to respond quickly to the changing customer demand and scale stock up or down.
  • Reducing manual work: because of automated processes, manual work is reduced, resulting in a decreased risk of human error.
  • 24/7 access to data: always insights into the data of the inventory gives practical benefits to get a competitive advantage.
  • Prevent overstock and understock: automated inventory management ensures the storage space is effectively used and knows what products to restock at the right time.
  • Easy integration with current systems: most companies already make use of ERP and CRM systems, which integrate easily with an AI application in inventory management (Serheichuk, 2020).

Impact

With an efficient AI solution in the inventory management there can be significant added value for the organization. Several case studies shows that inventory levels and holding costs could be reduced with 20-50%. Furthermore, a decrease of 15-30% in shipping costs can be achieved through improved real-time insight into stock levels and inventory in general. Moreover, companies note that service levels and On-Time-In-Full deliveries improve by 10-20% with an AI application.

Example

Coca Cola’s solution for cooling cabinets in retail outlets led to increased efficiency and less human work to keep up with the demand and needs of the customers. The tool enabled millions of retailers around the world to complete orders within a few clicks and rely on the calculations of the computer (Supply Chain 247, 2017).

With the help of artificial intelligence and big data the Swiss logistics giant, Kuehne + Nagel, improved their shipment planning and inventory management. Their AI solution enabled the company to find the best option for container shipping, including alternative routing options to adhere to transportation timeframes and reliability. A side-effect of implementation improved service levels of the company, because of better insights on shipment and inventory (Europawire, 2020).

Accessibility and Requirements

To implement an AI application, it is important to know that much of the required data is already in the company’s hands. However, the data is often not used or used incompletely by organisations. To train an AI application, different types of data suffice. Historical sales data, data on current supply and demand in the market and delivery times from different suppliers are all types of data that can be used.

To ensure that the AI solution works fully automated, the software has to be trained and needs to learn from itself. To automate, the inventory management process the system needs time and a lot of data. This requires knowledge on data science and analytics, datasets have to be extracted and combined with each other. Therefore, the AI solution is not just about importing data into the system, it also requires human work. The final decisions are made by the employees of the organisation, which requires insight and knowledge about the AI solution (Supply Chain 247, 2017).

To get the AI solution ‘up and running’ it is important that the machine learning model is developed. This model will be trained and will eventually make it possible to make use of the prediction outcomes in your inventory management. The model is developed in two steps:

Building a Machine Learning Model

To build a machine learning model, input data (e.g. sales data) together with historical results and a training algorithm are used to iteratively reach a prediction algorithm. The training algorithm will process the data and come to a prediction algorithm.

Source: (Subramanyam, 2019)

After creating a prediction algorithm. The model is now ready to receive unknown or new data input. The model will transform the data input using the prediction algorithm. What comes out is a prediction based on historical results. To improve the accuracy of a model, more data can be fed to the ML model that produces a prediction algorithm (Subramanyam, 2019)

Source: (Subramanyam, 2019)

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