Artificial Intelligence in Supply Chain Management

Introduction

Supply chain management (SCM) is critical in almost every industry today. Still, despite the importance, it hasn`t received the same amount of focus from AI startups and vendors as many other domains. However, given the vast amounts of data collected by industrial logistics, transportation and warehousing, this is an area with a lot of potential.

Digital transformation, digitalization, Industry 4.0, and such, these are all terms we have probably heard or read about before. However, behind all these buzz words, the main goal is the use of technology and data to increase productivity and efficiency. The connectivity and flow of information and data between devices and sensors allows for an abundance of available data. The key enabler is then being able to use these vast amounts of available data and extract useful information, making it possible to reduce costs, optimize capacity, and keep downtime to a minimum. This is where the recent buzz around machine learning and data analytics comes into play.

AI for the supply chain

Like in any other industry, the current focus on digitalization is transforming supply chain management also. Improving the efficiency of the supply chain is of great importance for many companies. Operating within tough profit margins, even slight improvements can have substantial impact on the bottom-line profit.

One of the examples where data analytics and machine learning can be beneficial for supply chain management is within demand forecasting and warehouse optimization. Given the vast amounts of data collected by industrial logistics, transportation and warehousing, being able to harness these data to drive operational performance can be a gamechanger for those that do it correctly.

Predictive analytics for demand forecasting

To illustrate the use of AI / ML in the supply chain, a hypothetical case study focused on demand forecasting is considered. It includes a hypothetical retailer in Country A and includes individual stores on various locations as well as a main central warehouse, all in Country A.

One of the challenges for such a retailer is to optimize localized vs. centralized warehouse storage of goods. On the one hand, substantial local storage is expensive, on the other hand, relying mostly on centralized storage and running the risk of sold out items in the stores is another factor. Warehouse optimization is thus of great importance and having access to accurate sales forecasts would be extremely useful information.

In order to predict the number of sold items in the sales outlets for each item, the historical sales records might contain some hidden patterns that our machine learning model can pick up. And, if this is the case, the model can then utilize these patterns to make accurate predictions of future sales. We can use the historical sales records from, say, 2003 to 2017, as training data and try to predict the number of sold items during the last quarter of 2018.

Defining the machine learning model: Having defined the training data and our target variables (what we are trying to predict), we can then set up a prediction model that tries to utilize the patterns hidden within the dataset to predict future sales.

Time series forecasting: Time series forecasting is an important area of machine learning. It is important because there are so many prediction problems that involve a time component. However, while the time component adds additional information, it also makes time series problems more difficult to handle compared to many other prediction tasks.

There are several types of models that can be used for time-series forecasting. One of the popular choices is a “Long Short-Term Memory network”, or in short LSTM Network, which is a special kind of neural network that make predictions according to the data of previous times. It is popular for language recognition, time series analysis and much more. However, simpler types of models provide just as accurate predictions in many cases. Using models such as random forest, gradient boosting regressor and time delay neural networks, temporal information can be included through a set of delays that are added to the input, so that the data is represented at different points in time. Using the “Date” variable, we can also extract a few additional useful features such as day of the week, if the date is a national holiday etc., which adds useful information to our model compared to using the date alone. 

For mixed variable types, tree-based models are often a good choice. 

Conclusion

Whether one is interested in forecasting on the level of the individual sales outlets or the total / average sales for all sales outlets depends on the objective. If one is mainly concerned about optimizing the central warehouse, predicting the total sales might provide enough information, and digging into the details of the individual shops might be a time-consuming effort with little to gain. It all comes down to clearly defining the goals and focusing on the business problem one is trying to solve rather than the technology one uses to solve it.

The above use case example provides a brief introduction to just one of many interesting and useful applications of machine learning within the supply chain. In the future, machine learning will be used in many more ways than we are even able to imagine today.