Machine Learning in Supply Chain Planning

Machine Learning in Supply Chain Planning - square

Machine Learning in Supply Chain Planning

Are we ready? And if so what’s involved?

The evolution to using artificial intelligence and machines that learn in supply chain planning is inevitable. In fact, there are early examples of the potential of AI to improve both supply chain planner efficiencies and provide better or optimized supply chain decisions. The question is, are we, as a profession, ready to embrace Machine Learning? If so, what does that mean and how do we get there?

Machine learning is a type of artificial intelligence (AI) that gives computers the ability to learn without being explicitly programmed. Machine learning computer programs teach themselves to grow and change when exposed to new data.

The latest Gartner Hype Cycle, published in July 2016, shows Machine Learning approaching the Peak of Inflated Expectations. Gartner predicts that mainstream adoption of Machine Learning is at least five years away, potentially ten. Still typing “Machine Learning AND Supply Chain Planning” into Google delivers more 16,000 results in less than half a second. This is a topic that supply chain planning people are thinking, talking, and writing about. In reality, the supply chain planning mindshare spent on Machine Learning is miniscule compared to that spent on reducing costs, improving customer service, and driving new revenue. Type “Cost Savings AND Supply Chain Planning” into Google and you get 2.5 million results.  One could argue that Machine Learning could contribute to meeting cost, revenue and customer service goals, but clearly there’s more focus today on basic supply chain planning capabilities like Demand Planning, Inventory Optimization, Sales & Operations Planning, and Supply Planning and Optimization.

One way to get started with Machine Learning is to look at your Demand Planning capabilities. For example, a “Best-Fit” forecasting algorithm automatically switches to the most appropriate forecasting method based on the latest demand information, ensuring you create the best forecast for every product at every stage of its life cycle. The algorithm evaluates forecast error each forecasting cycle and recommends or automatically selects the forecasting method that will produce the best forecast. “Best-Fit” forecasting is a basic form of Machine Learning.

Another example of today’s Machine Learning capabilities is found in software solutions that use algorithms to continually analyze the state of your supply chain and recommend or automatically execute plans to meet customer requirements. Optimization driven by algorithmic planning is an early form of machine learning that relies on a set of provided information (supply chain facilities and capacities, transportation lanes and capacities, customer service requirements, profit requirements, etc.) to automatically make optimal decisions.

One powerful example is the use of Multi-Echelon Inventory Optimization (MEIO) to automatically adjust inventory positions. The current inventory-to-sales ratio in the United States sits at 1.41, higher than any time since 2009 (right after the 2008 downturn). One cause of this glut of inventory is the emergence of omni-channel retailing. The “Amazon effect” of free and fast shipping, easy returns, and everyday low prices has changed customer expectations and the way products get into the hands of the consumer. It’s a struggle to keep up with the mind-bending rate of change that prevents companies from having the right inventory positioned at the right location to service customers. Companies that respond by increasing buffer inventory based on outdated information fail to attack the underlying issue of stock-outs, a fundamental shift in fulfillment. MEIO automatically seeks the optimal balance of inventory at the right locations, and provides optimal inventory parameters and positions by stocking location to establish optimal buffer locations and quantities. Embracing MEIO can reduce total inventories by upwards of 30% while maintaining or improving customer fill rates. MEIO is an example of basic Machine Learning that is available today.

Attaining the full benefits of Machine Learning will be an evolutionary process. We must learn to crawl, then walk, then run. The introduction of Machine Learning into most supply chain organizations will take years, but that shouldn’t stop supply chain professionals from planning for the future or taking advantage of some of the Machine Learning solutions available today. Implementing algorithmic planning and optimization technologies today builds the kind of expertise and experience that will ease the adoption of advanced Machine Learning solutions in the future.

Are you considering Machine Learning solutions?  If so, what steps are you taking to get there?

 

About the author 

Hank Canitz PictureHenry Canitz is The Product Marketing & Business Development Director at Logility. To read more of Henry’s insights visit www.logility.com/blog.

Advertisements

Removing the Two Barriers to Optimising Inventory

Removing the Two Barriers to Optimizing Inventory

Removing the Two Barriers to Optimising Inventory
Caught Between a Rock and a Hard Place

Henry Canitz – Product Marketing & Business Development Director, Logility

Supply chain leaders often find themselves in a difficult situation when it comes to the conflicting goals of improving customer service and minimising inventory. The omni-channel world we live in has driven customer service to new heights. Companies that don’t prioritise providing what the customer wants when they want it will soon find themselves losing market-share. On the other hand, product lifecycles continue to accelerate and the penalty for carrying too much of the wrong items leads to high levels of obsolescence. This isn’t a new dilemma, the balancing act between inventory and service has been going on since the earliest days of commerce. However, the penalties for bad service and/or high inventory are growing more severe and the space “between a rock and a hard place” is continuing to shrink.

Because of variability in demand and supply, increasing customer service levels can lead to higher levels of safety stock. Improving cash flow by indiscriminately reducing working capital dollars can result in slashing the wrong inventory, resulting in lower customer service levels.

While some supply chain teams have conducted inventory optimisation (IO) initiatives to raise service levels while lowering inventory cost, others worry that they won’t be successful in the effort.

There are two common barriers that can prevent an organisation from reaping the benefits of inventory optimisation efforts:

  • IO success can be undermined by reliance on:
    • Limited tools (such as modules built into, or bolted onto, existing ERP systems)
    • Inadequate solutions (e.g. error-prone, hard-to maintain spreadsheets)
    • Black-box systems (where calculations are difficult or impossible to validate)
  • An internal perception that understanding and implementing proven mathematical tools and business processes in order to streamline the creation of optimal inventory policies and targets is too difficult for the team to take on.

Overcoming these barriers is easier than you think and the benefits are too good to ignore. Companies that embrace Multi-echelon Inventory Optimisation (MEIO) achieve, on average, a 28% increase in inventory turns.

A simple three-step approach can remove barriers to achieving a successful MEIO initiative.

  1. Understand your current state and lay the foundation for a solid business case. Assess your organisation’s capabilities from the perspectives of:
    • Inventory performance
    • Business process and inventory management expertise
    • Technology and organisational readiness.
  2. Create a future state inventory optimisation capability—process, technology, organisation—that provides your supply chain team with a roadmap to success.
  3. Continue to drive fundamental strategic changes that create greater resiliency and agility throughout the supply chain and establish a cycle of continuous improvement.

Can you overcome the two common barriers to implementing inventory optimisation capabilities and get out of being Between a Rock and a Hard Place? Of course. We work with companies around the world who are driving significant value from their MEIO process.

Learn More:

 

About the author

Hank Canitz Picture

Henry Canitz is The Product Marketing & Business Development Director at Logility. To read more of Henry’s insights visit www.logility.com/blog.

Food & Beverage: Five Ways SYSPRO can Alleviate Your Headaches (Part 2)

whiskey-2382370_960_720

Part 2 – view part 1 here

SYSPRO’s association with process manufacturers is longstanding, and we continue to enjoy significant growth in our food and beverage customer base. I tend to think that we attract food and beverage customers with our industry-specific functionalities, our service, and the modular, cost-effective nature of our offering. SYSPRO’s enviable track record of retaining customers through periods of growth I credit to the scalability of our solutions, and to the dedication of our service representatives.

In my last blog, I discussed ways that food and beverage companies use SYSPRO to optimise traceability and trade promotions. Today I’m going to move on to cost control and inventory optimisation, and finish up with a short discussion of the Cloud.

Cost Control

It’s easy for costs to skyrocket, and the reasons are not always obvious. SYSPRO, integrated across an entire food and beverage company, provides 360-degree visibility into every facet of accounting, distribution and operations, unveiling important insights into metrics such as job cost performance, margins and pricing. Process manufacturers often utilise LEAN methodologies, and SYSPRO’s 360-degree visibility gives manufacturers the power to go LEAN, further their LEAN aspirations, or simply streamline and optimise their value chain.

End-to-end costing analysis allows manufacturers to assign more accurate production and overhead costs, and creates opportunities to eliminate redundancies, initiate improvement plans, and minimise non-value-add activities. SYSPRO can also facilitate the automation of processes that used to eat up surprising amounts of time, labour and resources, such as reconciliations, communications, paper-based documentation, etc. With an accurate picture of costs, it becomes easier to maximise profitability, even in a low margin environment.

SYSPRO’s bill of materials (BOM) provides detailed costing and an expected cost at each level of a production run. The Work in Progress (WIP) module, used in conjunction with the BOM, allows for the comparison of expected versus actual costs, often revealing realistic targets for cost savings.

One of my favourite SYSPRO tools is the Executive Dashboard. Dashboards are highly configurable, and give executives an ‘at-a-glance’ summary of complex information. In the office, at home, or on the road, dashboards allow managers to monitor key performance indicators (KPI) in real time. In addition, our ‘what-if’ costing features make it easy to compare the cost effects of different raw materials, production routes and labour rates. In a business environment as fast-paced and constantly changing as food and beverage, dashboards can shorten reaction time and decision making, heightening agility and giving the company a competitive edge.

Inventory Optimisation

One of the biggest balancing acts in manufacturing is inventory management, with some companies carrying as much as 50% of their capital in inventory. Those making proper use of SYSPRO, however, are usually able to minimise their inventory investment, while still maintaining appropriate levels of stock for demand management capability.

The inventory managers I know appreciate the fact that SYSPRO helps to determine optimum levels for basic, seasonal and safety stock, by factoring in metrics such as target service levels, depletion rate, order lead time and standard demand deviation. By connecting the inventory system to Order Entry, book inventory becomes an exact image of real inventory, providing unprecedented control over inventory and its associated costs. In addition, SYSPRO is an enormous help in enforcing a FIFO (first in-first-out) methodology, and in tracking expired product.

SYSPRO Inventory Forecasting predicts future sales based on historic demand. With Forecasting, managers can identify important products based on factors such as sales value, gross profit, quantity sold and cost of sales. In my experience, Pareto analysis – the famous https://en.wikipedia.org/wiki/Pareto_analysis – 80/20 rule – can really help clear the cobwebs from an outmoded view of a company’s inventory management.

Transformation on the Cloud

By now, you are probably aware that the Cloud can save money on capital expenditures. Not needing a server room, servers, and a high-paid IT department can be a major relief to the old P&L. There is also no doubt that the Cloud provides food and beverage companies with efficiencies that help them to scale. Efficiency and cost reduction, however, are only part of the picture when it comes to Cloud services.

We’ve all read articles, some of them verging on science fiction, about the oncoming ‘Fourth Industrial Revolution’. Whether you buy into the vision or not, there’s absolutely no doubt that manufacturing is changing to embrace new technologies, including automation, artificial intelligence, robots, blockchain (or blockchain-type technologies) and the Internet of Things. It is time, I think, to talk about the Cloud as an enabler of business transformation.

In the last few decades of the 20th century, companies made the choice to stick with their old, manual methodologies, or to join the IT revolution. Those that chose to transform were more likely to thrive. Of those companies that chose not to transform, very few are still around. In my opinion, we are now sailing similar seas – most companies cannot afford to ignore the advantages that accrue on the Cloud. Fortunately, SYSPRO ERP Cloud Services have been designed to provide a seamless, painless and profitable transition into the new manufacturing paradigm.