The document discusses optimizing logistics processes through mining business transactions and determining optimal inventory levels. It involves four main steps: [1] process mining transaction data to create process models, [2] identifying business transactions within the data, [3] mining statistics on transactions, and [4] calculating optimal stock reorder points using a formula that considers factors like lead time, demand, and required service level. The overall goal is to find bottlenecks and optimal inventory levels to improve logistics efficiency and service levels.
The Codex of Business Writing Software for Real-World Solutions 2.pptx
Slides of EEWC 2017
1. Optimization of Logistics Processes
by Mining Business Transactions and Determining the Optimal Inventory Level
Linda Terlouw (linda.terlouw@icris.nl), www.icris.nl
3. situation
How do we get the right material to the right place at the right moment?
4. situation
How do we get the right material to the right place at the right moment?
mechanic:
“I want a service level of 100%!”
logistics officer:
“We don’t have enough money!”
14. The directly follows graph is just a simple transformation and
visualization of the data using a weighted directed graph.
the inductive miner
Making the directly follows graph
15. the inductive miner
The inductive miner finds process models from event logs using a
recursive algorithm
22. finding business transactions
- Are coordination acts explicit or tacit?
- How can we map events to coordination and production acts?
- Are declines, rejects, and cancellations allowed?
- How does the process flow found by ‘normal process mining’ relate to
the process tree used in DEMO?
25. the stock reorder point
n = L (d/D) + σ [Φ(S)]
where:
- L is the lead time in days,
- d is the annual demand for the item,
- D is the number of working days in a year,
- σ is the demand standard deviation (per lead time),
- S is the required service level,
- Φ is the inverse of the standard normal distribution.