Demand planning in Logistics: Tesco and Otto
Demand planning is key in the supply chain management process. Its aim is to generate well founded forecasts, this way companies are able to reduce inventory stock outs, minimizing safety inventory levels, arranging production efficiently, avoiding costs over out dated products, organizing transportation more effectively or even using forecasts to take decisions on promotions, pricing and purchases.
One example that we found interesting regarding demand management is Tesco. In 2013, Tesco started using big data to plan demand and improve efficiency. They use a combination of data obtained from different sources such as mobile phones, social media, internet searches, weather information and also internal data regarding their sales in each store.
Using algorithms the company has managed to improve stock levels for each store and particular product.
One example of their improved efficiency is that the program increases the demand of products on promotion to avoid running out of stock or helps finding out which products should be sold at discount when they are approaching the sell-by date.
Tesco also plans demand according to regions, for example, stores closer to the sea have more stock of swim-related products.
Tesco, as many other companies, uses information technologies (IT) to plan production and forecast demand. It allows the company to reduce costs and increase profitability. These technologies enable the company to have real time information about stock levels, thus reducing inventory holding costs. Moreover, it reduces the number of manual activities that have to be made as orders are automatized.
Another relevant example is the case of Otto, which through demand forecasting has been able to increase significantly its savings. Nowadays, managers from the differents departments in Otto are highly interested in forecasting demand, since they have experienced the positive impact it has had applying predictive analytics into the managing process.
Otto is now using a dynamic pricing system in the menswear department, which has lead to an increase in the level of sales thanks to predicting how much are people willing to spend on the different catalogue products. This way adjusting prices to the demand trends of the menswear segment of the market.
Moreover, lately they have been running several analytical projects in order to improve the prediction of demand. The analyst's aim nowadays is to predict the level of return rates over the different catalogue products through analyzing data over the last 10 years. After analysing the data, they have reached some conclusions about the different cases when people might return clothes after its purchase.
One interesting result is that they found there existed a correlation between the number of products not being delivered on time and the level of products being returned. Thus, after observing this results Otto reduced the level of late deliveries by working with logistic providers trying to be more effective. As a result now their costs of returned products have been highly reduced.
To conclude, we can say these two companies, Tesco and Otto, have gained a competitive edge over its competitors due to demand planning. So, nowadays, using big data systems to forecast demand is key to succeed in the market. Thus, it is show to have a huge positive impact over the results of the companies, as they became more cost effective and productive in terms of supply chain management.
Alba Castanyer
Carla Casas
REFERENCES
Demand planning, The difference between demand planning, forecasting and S&OP:
UKEssays, Tesco logistics analysis: https://www.ukessays.com/essays/management/the-logistic-operations.php
Improving the planning process at Tesco, 2007:
Analysis: How Tesco and Otto are using data to forecast demand, Matthew Chapman:
Great post! It's clear that choosing the right demand planning model can make a huge difference in operational efficiency. I'm excited to see more content on how to optimize these models with new technologies.
ResponderEliminar