AI, Tariffs and Supply Chains in Knowledge Graphs

maxdemarzi 154 views 40 slides Mar 07, 2025
Slide 1
Slide 1 of 40
Slide 1
1
Slide 2
2
Slide 3
3
Slide 4
4
Slide 5
5
Slide 6
6
Slide 7
7
Slide 8
8
Slide 9
9
Slide 10
10
Slide 11
11
Slide 12
12
Slide 13
13
Slide 14
14
Slide 15
15
Slide 16
16
Slide 17
17
Slide 18
18
Slide 19
19
Slide 20
20
Slide 21
21
Slide 22
22
Slide 23
23
Slide 24
24
Slide 25
25
Slide 26
26
Slide 27
27
Slide 28
28
Slide 29
29
Slide 30
30
Slide 31
31
Slide 32
32
Slide 33
33
Slide 34
34
Slide 35
35
Slide 36
36
Slide 37
37
Slide 38
38
Slide 39
39
Slide 40
40

About This Presentation

How tarrifs, supply chains and knowledge graphs combine.


Slide Content

Supply Chain Management @ Yeti Coolers
Suppliers Manufacturing Warehouse Retail
SKU: Plastic
Site: Supplier, China
SKU: Plastic
Site: Supplier, Vietnam
SKU: Yeti Cooler
Site: Warehouse, Boston
SKU: Yeti Cooler
Site: Store, NYC
SKU: Yeti Cooler SKU: Pallet of Yeti Coolers
Site: China or Vietnam
Make Pack
Source
Source
Ship Truck
Plastic Moulding Machines Labor
Each part of the supply chain fulfill
demands, making intelligent decisions
on: What, How, When, Where and Why

The Supply Chain as Tables

The Supply Chain as a Relational Knowledge Graph
Relational Data Model Relational Knowledge Graph
Join → Relation Mapping
Named Relation
Table → Entity Mapping
Entity
Entity
Decomposed Entity
Entity
Externalized Relation

What is a Knowledge Graph?
1.Data: Nodes, Relationships, Properties, and Types
○Name is a string, DOB is a date, address is structure of strings and numbers, picture is a bitmap
○Person is named John, John was born in 1993, John lives in Atlanta, John looks like this ??????

2.Queries: “views” defined with queries, equations, and invariants
○Age = today - DOB – we can use queries to produce “data” or facts
○Person has only 1 DOB — it’s a rule/constraint/invariant
○Person has only 1 age – knowledge can be used to infer “know knowledge”

3.Intelligence: “views” using reasoning
○What is your age? Probably the average of your friends? (graph analytics)
○What is the fastest way to ship something below cost threshold? (solver based reasoning)
○What products will this person buy next week? (neural or probabilistic reasoning)
○Graph Analytics, Rules Based Reasoning, Prescriptive Analytics, Predictive Analytics

with Relational AI on Snowflake
An Intelligent Supply Chain Knowledge Graph

Add Business Logic
Using rules to connect the dots and derive rich context
Aggregate data over relations
Derive meaningful relations

Impact of Tariffs

China

Graph Analytics
Leveraging graph algorithms for deeper insights of the Supply Chain
Reachable Algorithm

Prescriptive Analytics
Mathematical Optimization
Optimized Supply Chain Plan

Predictive Analytics
Graph Neural Networks
Embeddings that capture the
information in the graph
How much demand will we
have next summer?


Classification
Link Prediction
Regression

What’s the
difference…
between
Predictive and
Prescriptive
Analytics?

I Decide
I Predict
Machine
Learning
Mathematical
Optimization

Talk to your Graph
Natural Language to
Relational Knowledge Graph Queries (Preview)