Mike’s Bikes – Stock Balancing

At Mike’s Bikes, the traditional method of planning bike allocation involved a time-consuming manual process. In an effort to streamline this process and enhance operational efficiency, Mike’s Bikes partnered up with the Datalab to implement an innovative solution.

As part of this initiative, we developed an algorithm to automate the bike allocation process. Our approach leverages data provided by Mike’s Bikes, including current inventory levels at their stores and distribution centers, historical sales data, and the target inventory levels for each store. By integrating this data, our algorithm identifies where bikes need to be reallocated most urgently.

The prioritization within our algorithm is structured around a hierarchical examination of product categories—from broad classifications like ‘Gravel Bike’ down to specific attributes such as model and size. Each category is evaluated based on the discrepancy between the actual inventory and the ideal inventory levels. The categories with the largest shortfalls receive priority, ensuring that resources are directed where they are most needed.

Moreover, the flexibility of our algorithm allows Mike’s Bikes to designate specific source and destination locations for the bikes, enhancing the effectiveness of redistributing inventory across their network. This could involve shifting bikes from distribution centers to stores, or between stores themselves, depending on where they are needed most.

The automation of the allocation process not only improves decision-making but also reduces the need for working capital and boosts overall profitability and customer satisfaction by ensuring better availability of bikes where they are most in demand.

  • Ellen Mik

    Senior Data Scientist
  • Thijmen van Es

    Data Scientist