top of page

AI Case Study

Alliance Boots achieves inventory savings and improved service levels with machine learning optimisation algorithm

Alliance Boots has deployed Manhattan Solutions' replenishment and demand forecasting technology, which leverages machine learning to analyse data and produce accurate forecasts. Through the solution, it has been able to reduce inventory and stock levels while also improve customer service and productivity across Europe.

Industry

Consumer Goods And Services

Personal And Household Goods

Project Overview

According to Manhattan Solutions' Customer Case Study: "Manhattan’s Demand Forecasting and Replenishment enable Alliance Boots’ 15-person UK planning team to make highly accurate forecasts for each of the company’s 384,000 SKUs and 30,000 product lines.

Decisions about replenishing stocks are made from forecasts based on sales history, demand estimates and the potential effect of promotions. The Demand Forecasting component runs the forecast calculations and automatically suggests the majority of order quantities, whilst the Advanced Exception Management capability allows users to focus on the smaller but highly significant percentage of orders that can be expected as a result of store promotions or events that may trigger sudden swings in demand. This reduced user interaction has provided Alliance Boots with significant productivity improvements.

The Replenishment solution provides planners with advanced reporting functionality that allows them to filter large amounts of data and generate spreadsheet reports, whether on forecast accuracy, out-of-stocks, overstocks, service levels or supplier performance.

Manhattan’s solution provides visibility into network demand and combines innovative forecasting techniques with demand cleansing, seasonal pattern analysis, and self-tuning capabilities to accurately anticipate demand even in the most complex scenarios. Using machine learning to constantly evolve and adapt the science of demand forecasting, our customers benefit from higher degrees of forecast accuracy, without heavy user intervention.

Manhattan simplifies the complex science behind Demand Forecasting by focusing the analyst on managing just those key exceptions that the system itself cannot reconcile. It becomes easy to manage an infinite combination of locations and products with differing time horizons and aggregation to enable assortment, financial, and merchandise planning, in addition to replenishment."

Reported Results

"In the ‘post go-live’ period, Alliance Boots reported it had reduced the amount of inventory it holds in the UK, whilst maintaining customer service at a consistently high level. Quicker and more accurate forecasts had a very positive impact on the replenishment process, with stock-outs reduced significantly."

Technology

Manhattan’s Order Streaming capabilities leverage machine learning to sense and adapt to changing conditions and priorities in the warehouse. Machine learning is used to predict the time required to complete work. An optimisation algorithm then uses those results to balance competing requirements while optimally utilizing available capacity.

Function

Strategy

Data Science

Background

"Alliance Boots decided to redesign its European logistics function and replace the Group’s various proprietary replenishment systems. The solution would enable the group to:

* Better identify and exploit buying opportunities
* Reduce inventory levels
* Improve service levels
* Improve replenishment processes
* Gain a much clearer understanding of stock value"

Benefits

Data

Sales history, demand estimates and the potential effect of promotions

bottom of page