Prevent Labor Cost Overruns through Data-driven Insights

October 18, 2019 5 Minutes Read

Retail industry’s traditional logistics and supply chains need to revamp if they want to keep budgeting issues, workforce allocation and competition at bay. Retailers are experiencing a fundamental change, with priorities shifting towards a customer centric approach as Industry 4.0, Internet of Things (IoT), Artificial Intelligence, Big Data and Machine Learning are influencing how businesses organize and collaborate.

While emerging technologies continue to drive the logistics and supply chain, it’s the human workforce factor that’s becoming a major concern for brands. Brands are turning towards slashing labor costs to reduce their budget but in the long run end up with low customer experience satisfaction, lost sales and profits. Can they afford this in light of the highly competitive omnichannel retail environment?

That’s what led a top retail brand to opt for Kloud9’s expertise in these technologies to help in managing the complexities involved in labor scheduling and budgeting to enhance productivity and reduce costs in their logistics and supply chain management.

Cost and productivity face the budget axe

One of America’s largest fashion retail brand had a revenue leak in their distribution centers where the staffing schedules were not in sync with the supply chain and logistics schedules of their retail merchandise. They needed a solution that optimized the monetary cost associated with trucks arriving at the store with less than the actual packaged units that were forecasted. By accurately predicting the requisite number of personnel/staff needed to handle the merchandise from unloading, to dispatching to the stores and stacking them, they wanted to reduce the cost factor involved.

The goal was to achieve a productivity planning dashboard that presented an overall 360 degree view into their supply chain and logistics management.

Machine Learning based model to the rescue

The traditional path that the brand followed involved staffing decisions based on previous schedules to handle the merchandise at the dispatch centers during both the anticipated rushes and the off-season lulls. This just adds to the cost with respect to arranging the workforce needed for a given day, week or month.

By performing last minute labor scheduling, the brand faced spiraling costs to meet the customer traffic flows that in turn affected the retail sales potentially leading to labor-to-traffic mismatches.

Kloud9’s solution was a machine learning based model that utilized historical data to more accurately forecast/predict the units delivered in order to improve the associate scheduling/planning and save money. This model accurately predicted the arrival of the shipment thus reducing the uncertainty in the workforce scheduling.

Machine Learning algorithms like the Time series (Naïve method, ARIMA, ARIMAX), Regression (Multivariate regression, Random forest, Extreme Gradient Boosting) were employed to develop the model.

One-time batch processing using Python language was used on data sourced from EDW and multiple data sources stored in cloud SQL.

Based on the historical data & root cause analysis, we developed an ML-based model that accurately predicts the number of packages per purchase order. Once the ML algorithms were used on the processed data to provide insights on the order and shipment data for further analysis.

This ultimately had the brand in curtailing their labor, shipping and logistics costs by accurately predicting the number of packages per order that arrived at the stores as well as the manpower required for performing the operations.

Success metrics used to measure the outcome of the excercise:

  • Raw model accuracy measured % unit variance to actuals
  • Keep associate hours on target (±12 hours)
  • Labor hours to labor dollars (Prevent underfund or overfund)

To successfully anticipate the customer demand based on insufficient information, and try to predict how much they will actually want is what retail brands must foresee. They have to take into account the complex factors like staff personnel, logistics and supply chain to ensure that purchase order is delivered correctly and on time.

At every stage of the supply chain there are possible fluctuations and disruptions, which in turn influence the numerous supplier orders. Using Kloud9’s expertise in providing retail solutions, brands can stay on top of their cost management solutions.

About Us

Kloud9 helps retailers build an ecosystem on Data Science, Machine Learning and Cloud. As your trusted advisors in digital transformation, we are determined to build a deep partnership along the way. Let our Machine Learning and Cloud experts assist you in unlocking the value of your data in new ways and accelerate your journey to Artificial Intelligence.

Kloud9 gives you the insight into what your business needs and requires

Kloud9 gives you the insight into what your business needs and requires