Quantitative Approaches to Supply Chain Management Flashcards
Supply Chain
A network of connected and interdependent organisations mutually and cooperatively working together to control, manage and improve the flow of materials and information.
Goals in Supply Chains
Decrease costs:
Travelling
Legal
Storage
Labour
Resilience
Sustainability
Common to these problems are: the concepts of trade-offs, incomplete information, and information asymmetry
Bullwhip effect: supply chain problemthat makes small demand changes cause big inventory fluctuations
Shortage gaming: customers place multiple orders for a product with one or more suppliers or when they place an order for more than what they want. This very real problem occurs often in businesses where shortages are expected, and the effect ripples throughout the supply chain.
Double marginalisation: multiple layers of a supply chain each mark up the price of a product, leading to higher prices for the end consumer than would occur with a more efficient or coordinated supply chain.
Quantitative Decision Making
Strategic
Product Portfolio
Make or buy
Supplier selection
Tactical
Outsourcing
Warehouse
Transport
Services
Offshoring
Operational
Forecasting for capacity and resource planning
Inventory orders for each location
Distribution planning
Service and maintenance planning
Consolidation Problems
Process of combining related activities or materials to improve the performance of a supply chain according to some measure
Material consolidation
Consolidate products
Consolidate buyers
Consolidate suppliers
Inventory consolidation
Facility location problems:
Centre of gravity
Euclidean distance
Postponement: play around with the state of the material to decrease the cost
Keep undyed raw material that is cut roughly at a further away location
Need a large scale to do
Transportation consolidation
Shipment consolidation
Order consolidation
Assume
Demand certainty
Supply certainty
Constraint costs
Span of control and visibility
Available and Emerging Tools
Descriptive: satatistical
Forecasting (mostly demand)
Linear regression, ARIMA models
Optimising decisions:
Mathematical: Mixed integer linear problems
Heuristic and nature-inspired: Genetic algorithms, Tabu Search, Particle Swarms…
Simulation
Monte Carlo, Discrete Event Simulation
Descriptive
Data mining
Complex network analysis
Prediction (demand but also…)
Supplier performance, Buyer performance/ behavior, Prices / CCC…
Machine learning (Regress, Classify, Cluster)
Optimising decisions
Reinforcement learning
Decision actuation with autonomous systems (e.g.RPA
Simulation
Multi-agent Simulation, Digital Twins
AI and Data Science
Descriptive
Predictive
Prescriptive
Predictive Supply Chain Risk
Complimentary approach to cascades analysis: delay prediction with data available to OEM
Data Imbalance
Engineering features: #WH served, #products, late orders given to suppliers, Supplier Agility
Prescriptive: Freight Sharing
Challenges
Data infrastructure
Skills
Firefighting
Misaligned goals
Lack of ecosystem perspectives
