We use cookies to give you a better experience. Carry on browsing if you're happy with this, or read our cookies policy for more information.

Skip main navigation

AI technologies and the supply chain: data analysis

An overview of the different contributors to the supply chain and what type of analysis they might need.
What is the role of AI in the supply chain of milk? To start solving the problem of how to get the right amount of milk from the farm to the local supermarket at the right time we first need to consider what analysis each stage of the supply chain might need. We need to know what we need to know so to speak. Each of the contributors to the supply chain need a different level of analysis so lets explore this in more detail. Local shops are interested in availability and price from their suppliers and daily or weekly total sales. They need to be able to supply local need or people may shop at alternative locations.
Distribution centres are interested in regional variations in sales and production. They need to match available product with need so as to not overstock and waste or under stock and let customers down. Bottling plants are interested in maximum consumption in their supply region. They need to time incoming deliveries, ensure the production equipment keeps up with demand, have enough packaging whether bottles or cartons and ensure timely sales deliveries. They may also have purchasing contracts extending months into the future. Delivery companies likewise need to ensure enough vehicles of the correct type are available and plan collection and delivery routes to minimise cost and environmental impacts. Farmers have long term planning to consider. How much land do they need to support the animals?
How many animals do they need? What do they do with the surplus? What if they under produce. This has been the source of much controversy as supermarkets use their buying power to drive down prices knowing that farm planning is a long term strategy. Selling at a small loss is better than not selling and suffering a large loss. We should also remember that not all data is internal to our supply chain for example, all the above scenarios could be affected by the weather which is not only beyond our control but this data comes from external sources. Governments use data to inform agricultural policy subsidies etc. They have an overall responsibility to Ensure the country is producing what the country needs.
In the first week of this short course you will ensure you could use AI to run analysis that gather the right data for optimising the supply chain.
In this video, we return to the story of the milk supply chain to explore what type of analysis the different contributors might need.
As mentioned earlier, understanding our target analysis is essential to ensuring we have the correct data available. In data analytics, we often just explore the data and see what drops out, but when you have a business problem you wish to solve using Artificial Intelligence (AI), you must ensure that the analysis is feasible: you must understand the data required, its source, its volume, its veracity and its variety (also known as the ‘3Vs’).
As you saw in the video, different businesses require different analyses to solve different problems. Often, this data will come from outside your own business, so it’s important that you are able to define the data you require to ensure it is gathered at the correct time, in the correct format and with the required precision.
There will also be times when we can summarise data and do not need an extreme level of detail – are we looking at daily, weekly, monthly, decadal analysis? Summarising data helps reduce the volume of data analysed and speeds up the analysis process.

Your task

Search for the different ‘V’ definitions – the 3Vs referred to in this article, IBM’s 4Vs and Microsoft’s 5Vs – and consider how they affect the data requirements.
Share your findings with other students in the comments.

Further reading

If you want to learn more about algorithmic approaches to problem-solving, you might want to read:
Alam, M. (2019) ‘A Data Science Project Cycle’. Medium [online] 6 December. available from https://towardsdatascience.com/a-data-science-project-cycle-af5a1cdef14f [22 April 2020]
This article is from the free online

Using Artificial Intelligence (AI) Technologies for Business Planning and Decision-making

Created by
FutureLearn - Learning For Life

Our purpose is to transform access to education.

We offer a diverse selection of courses from leading universities and cultural institutions from around the world. These are delivered one step at a time, and are accessible on mobile, tablet and desktop, so you can fit learning around your life.

We believe learning should be an enjoyable, social experience, so our courses offer the opportunity to discuss what you’re learning with others as you go, helping you make fresh discoveries and form new ideas.
You can unlock new opportunities with unlimited access to hundreds of online short courses for a year by subscribing to our Unlimited package. Build your knowledge with top universities and organisations.

Learn more about how FutureLearn is transforming access to education