In logistics services, the only way to grow is to reduce costs, as this is a cost centre for many managers. On average, in France and in all business sectors, logistics costs represent between 8 and 10% of sales. Data science and associated tools can help reduce these costs while improving customer satisfaction. This means faster delivery, lower costs and fewer errors.
Take, for example, a situation of over-stocking of maintenance parts in all warehouses: this implies high capital costs (space, obsolescence, etc.) and it is normal for companies to seek to optimise their inventory levels while guaranteeing a sufficiently high service rate. Once the best model is found for predicting the consumption of maintenance parts, the importance of business rules is critical for parts that cannot be modeled. We will also discuss the choice of an optimal model by the logistics team, which parameters are analyzed? Finally, successful integration of the model into the value chain is based on business ownership. Keep in mind that a model intelligence requires human intelligence to be adapted to a specific context.
10. The business analysis of the generated models
is fundamental to choose the optimal model
Stored
value
Service rate
11. The AI is not self-supporting in this case
Croston
modelisation
DECISION SUPPORT TOOL
Procurement…
Data consulting
Data science
Data consulting + training
1. 2. 3.
Addition of
business rules
Analysis and
use
In logistics services, the only way to grow is to reduce costs, as this is a cost centre for many managers. On average, in France and in all business sectors, logistics costs represent between 8 and 10% of sales. Data science and associated tools can help reduce these costs while improving customer satisfaction.
on the different storage levels since fewer parts in stock cost less but inevitably implies a decrease in the service rate.
Demand = stock consumption
As is often the case, maintenance parts have a sporadic consumption type, i.e. parts are consumed at very long and irregular intervals.
Intermittent demand forecasting
Given the particular type of coin consumption, the Croston model is the most appropriate and allows two independent predictions to be made: one for the value of each consumption and another for the interval between each consumption. The Croston algorithm updates the estimates of S and I following an order, and does not change them if on the other hand in the most recent period there was no consumption.
In both cases, prediction is an arbitration between the last prediction and the most recent observation; thanks to this exponential smoothing principle, historical consumptions receive variable weights according to their age in time.
Business knowledge of the type of parts stored and their consumption characteristics makes it possible to add rules to the model to adjust it more closely to business constraints
You’ll end up with a flow chart with a specific rule for each category of items
For example, For a very expensive item, not sensitive, and which is rarely consumed, it will be more reasonable not to keep stock. Being able to satisfy all orders in this category would explode the capital tied up.
The custom algorithm generates a number of models that test different combinations of parameters. These are the smoothing parameters of the model that give variable weights to historical consumption according to their age over time.
The performance of the calculated models is evaluated against the two KPIs initially defined: service rate and stored value.
Its use and exploitation require, on the one hand, adaptation to a business context and, on the other hand, the intervention of the business to analyse the results and implement them. This human added value will not be replaceable by robots.