Tesco is one of the largest retailers in UK. There was a substantial drop in returns from capital employed (ROCE), due to operational, regulatory and economic factors. The drop in ROCE was directly tied to the stock held in the depots. Hence an effective inventory management was the need of the hour. On realizing that, Tesco analyzed the sales data of the last four years that was held in a Teradata data warehouse. It ran simulations of the distribution depots using the Matlab modelling tools from MathWorks. This project enabled them to substantially reduce the stock levels and saved them around £50m. This was just one of the several projects that were simultaneously implemented.
The next project in inventory management involved understanding the correlations between sales and weather. For example, it was found that the demand barbecue food rise in warm weather, but the amazing part was the impact of location and context on demand. A warm day in Scotland will produce different demand to the same temperature in the South. Similarly, demand on the first weekend of a hot spell will be different to one in the middle of a heat wave. These findings were a result of regression testing.
Computer models produce a coefficient which is fed into Tesco’s live order management system, adjusting the amount suppliers are expected to deliver each day. Run on an IBM System Z mainframe, the system manages stock orders from thousands of suppliers, worth around £100m every day. Overall, Tesco uses supply chain analytics to save £100m a year.
It seems that the answer to every problem is optimization and analytics. Is there a saturation point beyond which analytics cannot help inventory management?
Watch this video of Mike McNamara (CIO - Tesco):
References:
1.http://en.wikipedia.org/wiki/Tesco
2.http://www.computerweekly.com/news/2240182951/Tesco-uses-supply-chain-analytics-to-save-100m-a-year
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.