CognitOps Insights

Leadership Walkout: Can machine learning in the Distribution Center help?

We live in odd times. A global pandemic shut not just all major cities, but countries down for months with people juggling remote working, children being at home all day, and the uncertainty of the economy. With this kind of not only economic, but personal financial uncertainty, one would imagine that employees would have done anything to “save” their job and ensure paychecks continue to flow in. However, as seen across news and editorial spaces everywhere, we are now talking about millions of workers quitting, relocating, and changing jobs in previously unseen droves.

The U.S. Department of Labor statics confirm that 11.5 million, that’s right, MILLION, quit their jobs in the 2nd quarter of 2021 and 2.9% of the labor force resigned their positions in August 2021 alone. A Gallup poll results indicate that 48% of employees are actively searching for new opportunities and that 38% plan to make a change in the next six months.

I was not surveyed, but having made a move myself recently, I would have fit perfectly into those statistics, as would six of my closest friends. One would think that this is rare, but according to an ABC News poll, over 40% of the workforce is quitting and relocating. This is not specific to the hospitality and travel industries but according to Fast Company research, retail, transportation, and healthcare are the hardest hit industries.

And, something that surprises many –it’s not specific to only front-line employees viewed at higher risk during the pandemic, but white-collar employees are seeking new opportunities in droves as well. According to research from, the ‘Great Resignation’ primary drivers are:

  • Personal safety
  • Lack of fair treatment
  • Horrible bosses (and no, not the movie)
  • Inequitable work-life balance
  • Remote options
  • Money

So why is this important to you, a logistics and supply chain leader? Sure, you have lost a lot of frontline workers – you are feeling the pain of peak season with numerous open positions. Your supply chain runs by incorporating people, processes, equipment, and systems altogether.

Your processes remain intact regardless of the Great Resignation. You are considering automation and more updated equipment and advanced software to fill in the labor gaps of frontline employees, but what about the risks associated with your distribution center leadership quitting? Turnover within the warehouse floor employees we are accustomed to – it’s been a serious challenge in the space for a while. However, leadership turnover presents a different set of challenges. Operations Managers, Supervisors, and Leads hold knowledge and skills that are attained through long day after day experience of trial and error of running complex operations. All this knowledge is often locked inside that individuals head and hopefully becomes tribal knowledge. This has now become a point of risk for the organization as 40% of the workforce is on the hunt for new roles. Every family and community knows the foundation and knowledge of ‘elders’ can’t be replaced if it isn’t transferred and actively maintained. But, how do we mitigate this risk in the face of these kinds of numbers, at this pace? What is available other than having all your leadership team write down every little thing they do, which beyond being impractical, wouldn’t be enough.

AI And Machine Learning for Warehouse Management: The Future of the Distribution Center

Here enters the future of warehouse operations leadership, artificial intelligence (AI) and more. Specifically, optimizing your operations by using machine learning for warehouse management. All distribution centers contain a system stack that collects and holds data. Data regarding transactions, inventory, and work in process. Warehouse leadership harnesses this data through historical reporting, Excel, real-time dashboards such as PowerBI. Armed with data and tribal knowledge of the processes and operations, leadership makes decisions regarding waving release, labor plans and shifts, equipment needs, and inventory placement. In the warehouse space, the time to complete this work is called pre-shift planning. It’s a daily task that requires leadership to come in hours before their shift and to monitor screens within their office during the shift to ensure performance metrics are met.

So, all that said – machine learning for warehouse management, how is this the answer? Solutions incorporating machine learning technologies utilize untapped data to learn processes, unique seasonality, order patterns, and performance capabilities to provide real-time forecasts, predictive analytics, and prescriptions to improve the operations or remove exceptions. This is all done behind the scenes and requires accurate data and minimal time for the software to fully “learn” but all can be done at relatively a lower cost compared to onboarding leadership, including the tribal knowledge.

Streamlining Decision-Making

CognitOps was built with the intent of simplifying leaderships role using MI to provide them with the data and actions needed to run distribution center operations with near real-time visibility across labor, orders, equipment and inventory as well as provide actionable recommendations during the shifts that will optimize labor, equipment, order processing, and inventory placement. Not only will the software enable smooth operation and reduce dependency on tribal knowledge but frees leadership to move about the operation to lead vs. being stuck within the office, working through data systems, excel, and historical data to make decisions. In totality, this allows for higher retention of a more engaged workforce, faster onboarding with access to tools that proactively serve deep insights and operational data, and higher efficiencies and productivity that can soften the impact of a labor crisis in the industry that doesn’t have an end in sight.  



Find the resiliency your operation needs with CognitOps. Get in touch here.

Daniel Johnson

Director of Sales