1. DSC Adria 2023
Nino Požar
Data Scientist & Product Owner, BE-terna
+385 91 4007 075
nino.pozar@be-terna.com
https://www.linkedin.com/in/nino-pozar
WHAT ARE WE SHIPPING –
FRESH AIR OR VALUABLE ITEMS?

2. 1. Introduction & overview
2. Transportation optimisation
1. The problem
2. Working example
3. Use case example
3. Conclusions
Agenda

3. Introduction
Challenge
1|DEMAND
FORECASTING
2|OPTIMISE
PRODUCTION
PLANNING
3|SCHEDULE
PURCHASE
ORDERS

4. Introduction
Challenge
2|OPTIMISE
PRODUCTION
PLANNING
4|TRANSFERS
BETWEEN STORES
1|DEMAND
FORECASTING
3|SCHEDULE
PURCHASE
ORDERS

6. ?
?
?
?
?

7. 1.
2.
5|TRANSPORTATION
OPTIMISATION

8. The problem
Bin packaging problem
Knapsack problem
Transportation

9. Transportation optimisation problem
Bin packaging & knapsack problem
Bin packaging problem
• items of different volumes must be packed into a finite number of bins/containers each of a fixed given volume
in a way that minimizes the number of bins used
• minimize the number of trucks (containers)

10. Transportation optimisation problem
Bin packaging & knapsack problem
Bin packaging problem
• items of different volumes must be packed into a finite number of bins/containers each of a fixed given volume
in a way that minimizes the number of bins used
• minimize the number of trucks (containers)

11. 0
1
2
3
4
5
0
1
2
3
4
5
0
1
2
3
4
5
20 14
20 11 19
4
23
10
3
Transportation optimisation problem
Bin packaging & knapsack problem
Knapsack problem
• given a set of items, each with a weight and a value, determine the number of each item to include in a
collection so that the total weight is less than or equal to a given limit and the total value is as large as possible
• fill trucks with the most valuable items
10 20
12
4 17
14
23
3
14
5
17
50
19
20 10
10 11

12. 0
1
2
3
4
5
6
0
1
2
3
4
5
6
7
0
1
2
3
4
5
6
7
8
9
20 14
20 11 19
23
10
3
17
20 14
20 11 19
4
23
10
3
Transportation optimisation problem
Bin packaging & knapsack problem
Knapsack problem
• given a set of items, each with a weight and a value, determine the number of each item to include in a
collection so that the total weight is less than or equal to a given limit and the total value is as large as possible
• fill trucks with the most valuable items
10 20
12
4 17
14
23
3
14
5
17
50
19
20 10
10 11

13. 0
1
2
3
4
5
6
0
1
2
3
4
5
6
7
8
2
3
4
5
6
7
8
9
20 14
20 11 19
23
10
17
17
20 14
20 11 19
23
10
3
17
Transportation optimisation problem
Bin packaging & knapsack problem
Knapsack problem
• given a set of items, each with a weight and a value, determine the number of each item to include in a
collection so that the total weight is less than or equal to a given limit and the total value is as large as possible
• fill trucks with the most valuable items
10 20
12
4 17
14
23
3
14
5
17
50
19
20 10
10 11

14. 0
1
2
3
4
5
6
0
1
2
3
4
5
6
7
8
9
0
1
2
3
4
5
6
20 14
20 11 19
23
10
17
17
Transportation optimisation problem
Bin packaging & knapsack problem
Knapsack problem
• given a set of items, each with a weight and a value, determine the number of each item to include in a
collection so that the total weight is less than or equal to a given limit and the total value is as large as possible
• fill trucks with the most valuable items
10 20
12
4 17
14
23
3
14
5
17
50
19
20 10
10 11

15. 0
1
2
3
4
5
6
4
5
6
7
8
9
0
1
2
3
4
5
6
Transportation optimisation problem
Bin packaging & knapsack problem
Knapsack problem
• given a set of items, each with a weight and a value, determine the number of each item to include in a
collection so that the total weight is less than or equal to a given limit and the total value is as large as possible
• fill trucks with the most valuable items
23
20 17 14
17
50 20 11 19
10 12
4
3
14
5
10
10

16. Working example
Ana
CFO
Bob
Purchaser
Dan
Warehouse mng
…and his colleagues
Transportation

17. A
A A
B
A
C
C
B
C
A A
A
C
C
C
C
1. First (current) order
2. Next order
Order priority
1. A
2. B
3. C
Classification priority
Ana
CFO
Dan
Warehouse mng
Bob
Purchaser
Round
SKUs!
A A
A
A
C
C
B
C
A
A
A
C
C
C

18. A
A A
B
A
C
C
B
C
A A
A
C
C
C
C
1. ROUNDING
C
2. Next order
Order priority
1. A
2. B
3. C
Classification priority
1. First (current) order
Ana
CFO
Bob
Purchaser
Dan
Warehouse mng
A A
A
A
C
C
B
C
A
A
A
C
C
C
Priority
SKUs!
Round
SKUs!

19. C
2. FILL THE TRUCKS
A
A A
B
A
C
C
B
A A
A
A A
A
A
C
C
B
C
A
A
A
C
C
C
C
C
C
C
C
C
C
C
C
C
A
A
A
A
A
1. First (current) order
2. Next order
Order priority
1. A
2. B
3. C
Classification priority
Ana
CFO
Dan
Warehouse mng
Bob
Purchaser
Fill 2nd
truck!
Group
SKUs!
Priority
SKUs!
Add
truck!

20. A
A
A
A
A
C
3. REARRANGE THE TRUCKS
A
A
A
A
A
C C
A
A
A
A
A
A
A
C
C
C
B
C
B
A
A
A
C
C
Ana
CFO
Dan
Warehouse mng
Bob
Purchaser
Group
SKUs!
Round
SKUs!
C C
C
C

21. A
A
A
B
A
C
C
B
A A
3. REARRANGE THE TRUCKS – ROUNDING
A
A
C
Ana
CFO
Dan
Warehouse mng
Bob
Purchaser
Round
SKUs!
Priority
SKUs!
C
C C
C
C

22. A | OOS
A
A
B
A
C
C
B
A A
C
A
C | OOS
C | ALERT
C
C
3. REARRANGE THE TRUCKS
C
A
A
LET'S
GO!
I’M
READY
Ana
CFO
Dan
Warehouse mng
Bob
Purchaser
Priority
SKUs!

23. Bob
Purchaser
How can AI help Bob?
Use case

24. Bob
Purchaser
• Bob is presented with results – BI application
Presented
with
results
Change & confirm
recomm.
Reoptimise
cargo
Check new
results
Confirm
results

25. Bob
Purchaser
• Bob is presented with results – BI application
Presented
with
results
Change & confirm
recomm.
Reoptimise
cargo
Check new
results
Confirm
results

26. Bob
Purchaser
• Bob is presented with results – BI application
Presented
with
results
Change & confirm
recomm.
Reoptimise
cargo
Check new
results
Confirm
results

27. Bob
Purchaser
• Bob is presented with results – BI application
Presented
with
results
Change & confirm
recomm.
Reoptimise
cargo
Check new
results
Confirm
results

28. Bob
Purchaser
• Bob is presented with results – BI application
Presented
with
results
Change & confirm
recomm.
Reoptimise
cargo
Check new
results
Confirm
results

29. Bob
Purchaser
• Bob is presented with results – BI application
Presented
with
results
Change & confirm
recomm.
Reoptimise
cargo
Check new
results
Confirm
results

30. Conclusions?
Possibility of controlling incoming orders
• Date of expected order arrivals
• Date of stock availability
Service level is increased
• Less delays in production
• Less delays in delivery
Advantage in managing warehouse
• Less jams in warehouses
Verification of orders through dashboard
• Ability to modify & recalculate
• Direct integration with ERP
Automation as the ordering procedure is
transferred into algorithms of ML platform
• Increases productivity
• Decreases manual work
• Quicker learning curve for new
purchasers (replacements)
Sustainability effect
• Decrease in carbon footprint Financial benefits
• Less money spent on transportation

31. Thank you!
Nino Požar
+385 91 4007 075
nino.pozar@be-terna.com
https://www.linkedin.com/in/nino-pozar