The Advent of Machine Learning for Supply Chain Planning

Shaun Phillips is an expert in Machine Learning technologies and is the Global Product Manager at DynaSys.

Machine Learning is an application of artificial intelligence in which system can learn from data without being explicitly programmed.

A major technology breakthroughs

In the past decade or so, there’s been some major technology breakthroughs in storage, in data and communications. The advent of hard drive that allows us to have write once, read many, fault tolerance, distributed storage at a very low cost. The extension of Moore’s law allows us to put up to ten million transistors on one chip. This allows to perform a huge amount of transactions over a large amount of data. This in itself, has led to Machine Learning.

Supply Chain Planning Challenges

At its essence, Supply Chain Planning is about balancing supply and demand. It could do it with a large amount of both historical and current real time data. With that data, there are trends, there are outliers, there are exceptions. With that data, there is a large number of questions to answer:

  • How much or less sell?
  • How much capacity will I have?
  • How long will it take to deliver?
  • How will this new product launch go?

Getting across all of that data we are able to make real decisions with it. This is where Machine Learning comes to play.

Machine Learning as a Solution

There is a very large number of potential applications for Machine Learning within Supply Chain Planning. Both supervised learning and unsupervised learning. We are currently engaged with our customers on several initiatives. One of these for example involves data cleansing. It identify missing, rogue, duplicate data points and uses history and historical actions to correct the data where that would have been done manually in the past. Machine Learning is also useful for augmenting decision making, such as new product launches. Machine Learning looks at the attributes of a product, the geography of a product, the correlating data, and make a decision on how a new product launch will behave.

A New Way of Planning

The future for Machine Learning with Supply Chain Planning will be very different but very exciting. It is a great time to be in the Supply Chain technologies business. The future of Supply Chain technologies will be highly automated and highly responsive. Machine Learning has the ability to recalculate and process large amount of real-time data. This data can potentially invalidate the current plan or identify a fresh opportunity for your current plan. Being constantly bombarded with these real-time impacts and opportunities will change the way we do Supply Chain Planning today.

The case for adopting Machine Learning techniques is logical, it is faster, it is cheaper, it is more accurate. It is less input for higher quality output. The case is very obvious.