In the first part, I primarily touched upon the limitations of current Off-the-shelf Inventory planning systems . That discussion laid the path to this second part-how we can leverage Machine learning to mitigate those limitations.
In this part, we will dive into the crux of it. How exactly we can leverage Machine learning to actually take Inventory Planning analytics to the next level.
Inventory Strategy formulation (an ideal approach)
Before we delve deeper into applications of machine learning in Inventory management, we need to understand what factors influence Inventory policies. As you can see in the illustration below, Inventory policies can’t be created in silo since there are so many strategies that influence your Inventory strategy.
For more in depth read on Inventory strategy and best in class process, you can review the following article: LinkedIn-Formulating an Inventory strategy
My firm belief is that current Inventory models, that use only a handful of standard parameters, are not equipped to help you plan a strategy that can be influenced by so many other strategies.
Leveraging Machine learning for Inventory planning will allow you to truly exploit the Big Data revolution
Organizations these days hold a massive amount of data but only a minuscule portion of that data set is used in Inventory models. A primary driver behind this is the capability of Inventory modeling systems . First, they are pre-built with limited input parameters. Second, even though the calculations are “automatic”, I don’t know of many organizations that will allow these numbers to flow directly into their buying systems. The fact is, sourcing professionals/planners in most organizations that use such tools know that these numbers can’t be trusted.
A Machine learning algorithm, that has been custom designed, is limited only by the computing power of the machine that runs it. Not only can it tap into and analyze hundreds of data points, the end users (say planners) can “train” the algorithm using their tribal knowledge. The same algorithm can be “trained” differently by each planner, based on the product portfolio that they plan for.
How machine learning can help us create the next generation of Inventory planning systems
Let us imagine that we have developed the tool that I envision. We will call our Machine learning algorithm “REALISTIC”. REALISTIC, unlike other Off-the-shelf tools, is not a cookie cutter tool. Its algorithm has been tailored to suit specifically your business needs and your business model. REALISTIC is fed Terra bytes of historical and current data pertaining to (not an exhaustive list):
SKUs– Description, weight, volume, primary packaging, secondary packaging.
Sales data: Historical sales data at SKUs level, by geography, weekly or daily level.
Manufacturing data: Production capacities historical data,current and projected capacities, at the production line level.
Transportation data: Actual historical data that has detailed info on what SKUs typically go by which mode, by carrier, for each lane. Carrier performance metrics history is also a critical part of this sub set of data. Historical and projected taxes, duties and surcharges will also be included here.
Economy and Market data: Market historical and projected data (growth/decline etc.), Economy trends and related for last two years and upcoming projections. Related trends, like carrier capacity crunch etc.
A little bit about reinforcement learning
In my example, I will use one specific machine learning methodology called Reinforcement learning. The focus of this article is to illustrate how Machine learning can help refine Inventory planning process so I will not get into the technical details of Reinforcement learning but below is a very brief explanation:
Reinforcement learning is a type of Machine learning algorithm whose objective is to maximize some long term reward. Having been trained with initial data, these algorithms begin by trying various actions, observe the resulting rewards from these actions and then learn to improve their actions accordingly. Important point here is that these algorithms are not programmed to execute any pre-determined strategy-they learn on their own.
Reinforcement learning based Inventory planning algorithm is not constrained by pre-defined Inventory policies
Because the world is not Black or White. Remember that some additional aspects were incorporated in Inventory models to account for variability-for example, lead time variability. However, we then apply standard approaches to calculate the variability (Standard Deviation, assuming a Normal distribution etc.), which essentially makes the very idea mute.
The excitement around Big Data is primarily due to the fact that given the right capabilities, each and every data point can be a contributor. A reinforcement learning based Inventory planning algorithm will have the capability to do exactly that. So we end up with:
- No need to create rigid product groups-each product’s unique characteristics can be analyzed and incorporated by the algorithm. However, if computational power and other resources are a constraint, the algorithm can then group products as well, based on various characteristics that go much beyond the brute force approach of creating product groups.
- No need to assign a pre-defined Inventory policy (like (s,S),(S,q)etc.). The model will make its own decision, based on millions (or maybe trillions) of values that it analyzes. It will maintain inventory levels at SKU level or Product groups based numerous input parameters. For each parameter, we feed it a gigantic amount of data, both historical and projections.
Reality of developing and implementing REALISTIC
Now comes the difficult part-how realistic is it to develop and implement something like this?
The key point to note here is that this will be a customized solution. Whether you need to invest in a capability like this or not depends on few aspects like (not an exhaustive list):
- Your product portfolio: There are several standardized approaches to Determining what type of products your portfolio has. If your SKUs have very predictable demand, you make to stock and the variability and unpredictability in your business model is minimum, you probably can keep leveraging the Off-the-shelf tools
- Size of your business: Investing resources into developing and implementing something of this scale can be daunting. Initial investments can be huge. And since these algorithms will take time to learn, there needs to be realistic expectations on the initial ROI. These factors make such solutions more compatible to large organizations who are willing and capable of investing time and money.
- Infrastructure: Let us be honest about this-your IT Infrastructure matters a lot as far as implementing any Machine learning algorithms go. It is not just about computing power but a plethora of other IT related capabilities like Data quality, inter connectivity of systems, real data data flows etc. Having a solid technology is one of the foundational aspects of implementing Machine learning tools so if you believe you are not there yet, take care of this aspect before moving on to the next milestone.
- Processes: Systems are built around processes (specifically, customized systems). You dont want to build an infrastructure around processes that are broken. If you processes, whether it is procurement or Inventory management, are sub par, your focus should be business process re engineering before you start modernizing/rebuilding systems around the processes.
- Talent pool: One of the most critical aspects is having the right type of talent that can support these tools of the future. Right type of talent does not mean more data scientists. It means that the end users are techno savy enough to understand what the tool is doing, how they can influence the algorithm to make it “learn” etc.
The Road ahead
My perspective is that it is high time we think beyond the archaic Inventory management systems that have bogged down the advanced in Inventory planning analytics so far. The technology and talent to support such an initiative is in place now-is your organization game enough?