Scribd
Upload
12 views3 pages

Model Answer

Uploaded by

hieubeo279
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views3 pages

Model Answer

Uploaded by

hieubeo279
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

LogisticAI

Deloitte Ireland
Executive
Top 3 components at risk
• AI engine
• Shipping database

Summary
• MongoDB database

Why they are at risk


These 3 components have 78-79% downtime, 37%
more than the next most risky component

Recommended actions
• Prioritise the quality of training data when training the AI engine
• Implement better database security measures
• Ensure that only valid keys stored within the databases
Components by % total downtime AI engine
79.1% downtime = 16.7% of total
Has a huge downstream impact since the output of the entire
SMS system is reliant on AI. Furthermore, bad quality predictions may
7.7% cause regulators to be wary of the system.
Customer AI engine
database 16.7%
8.1%
Shipping database
Web frontend
79% downtime = 16.7% of total
8.3% If this goes down, the AI engine won't be able to produce output
Shipping due to only having a partial dataset and the Django controller won't
database
Android frontend have the information needed to provide to the shipping
8.4% 16.7%
management system (SMS).

Django MongoDB database


controller
MongoDB 78.9% downtime = 16.7% of total
8.7%
iOS frontend database If this goes down, the machine learning models, metadata and
8.8% 16.7% parameters will be unavailable for the AI engine, rendering it
useless. Since LogisticAI's output is heavily reliant on the AI engine,
the whole system is affected if this goes down.

You might also like