A new approach to inventory signals a bottom line boost
A large, international distributor had experienced consistent double digit annual growth but was yet to generate positive cashflow. Its rapid growth and long supply chain had meant that its working capital and more specifically its inventory levels had ballooned to absorb any free cashflow the company was able to generate.
When the company’s board decided to launch a concerted effort to reduce working capital the company enlisted our help to improve its inventory ordering rules and policies.
Higher service levels, lower inventory
A hybrid team of consultants worked with the company to identify where it had accumulated bloated inventory levels and what the root causes were of build ups were. This led to a deep dive analysis of how the company currently forecasted demand and generated orders to pinpoint the barriers to better accuracy.
The company regularly needed to estimate what its retail store customers would order three months out, both by SKU and depot combination, amounting to roughly 18,000 individual series to forecast. Using manual tools, forecasts and orders were based primarily on procurement staff discretion. In addition to being inefficient, procurement staff added large buffers to ensure their forecasts didn’t fall short.
We worked together to redesign the company’s data collection and modeling process, harnessing machine learning techniques to automatically flag and adjust input data and select an appropriate algorithm for each data series. We ustilied statistical models to set safety stock and re-order levels that avoided inflated orders whilst maintaining the same level of service.
Whilst the project is still in the implementation phase, it is forecast that the revised inventory ordering techniques will reduce overall inventory levels by 20% whilst maintaining customer service levels of 95%.