The practice of slotting in the warehouse refers to determining the optimal placement for every item. The understanding of slotting and its inherent advantages can be somewhat obvious, but optimizing it can be a constant challenge due to the incredible number of variables, dependencies and layers of complexity. Let’s look at the root causes of some of that complexity and then explore how applying machine learning and AI can be the perfect solution.
The Challenges of Improving Slotting
Proper product slotting enhances labor productivity, DC throughput, and order accuracy. But doing it well hasn’t been easy. Optimal placement of products within the warehouse, or slotting, has a significant impact on all the warehouse key performance indicators – productivity, shipping accuracy, inventory accuracy, warehouse order cycle time, and storage density. Yet, typical warehouses have fewer than a third of items located in optimal locations. This includes those that put effort into slotting via spreadsheet calculations and even slotting software packages. How could this be?
The answer is that slotting is a very difficult problem to solve with traditional approaches. It is both what’s called a combinatorial optimization problem (many input factors to consider) and a multiple objective optimization problem (many goals, sometimes competing). On top of that, there are typically thousands of products and slots involved. All this adds up to the fact that we have a complex problem with a very large set of possible answers. This is the kind of problem that AI excels at solving and the kind of problem that traditional approaches struggle with.
Machine Learning in the Slotting Process
But AI can bring more to the table than better slotting results. For example, it can lower implementation costs as it does not require a detailed CAD drawing of the warehouse, as is the case with traditional slotting software. Instead, with AI-based slotting solutions the spatial characteristics and travel time predictions can be automatically learned based on machine learning and activity-level data generated by modern work execution systems.
Although there will be some variability, in most cases AI-based slotting can deliver 10-20% labor cost savings. That is in addition to a 1-5% improvement in accuracy. Finally, AI drives advanced machine- learning algorithms to recommend the best locations for your inventory based on SKU velocity, SKU affinity, product/slot information, pick paths and other data, bringing a 20-40% increase in throughput.
That’s a powerful case to make for utilizing AI in your slotting operations. Better yet, the model adapts to your DC and evolves as conditions change, providing continuous optimization.
In our final post in the series, we’ll explore travel optimization and its potential to drive up to 50% savings in labor costs, as well as increasing throughput by up to 100%.
To get a more in depth understanding of AI and the benefits it can provide in your operation, check out our Achieve Your AI Potential white paper, and stay tuned for the final post of our Fast Start Opportunities for AI blog series.
About Lucas Systems, Inc.
Lucas Systems helps companies transform their distribution center operations and continuously adapt to changing market dynamics. We dramatically increase worker productivity, operational agility, and customer satisfaction.
Our solutions are built on 23-plus years of deep process expertise and smart software using AI and voice technologies. Our solutions feature Jennifer™, the brain, voice, and orchestration engine that drives performance improvement gains. Make the smartest moves at the lowest cost with Jennifer™. For more information, visit www.lucasware.com.