CertNexus AIP-210 Exam - Topic 6 Question 24 Discussion

Actual exam question for CertNexus's AIP-210 exam

Question #: 24
Topic #: 6

A company is developing a merchandise sales application The product team uses training data to teach the AI model predicting sales, and discovers emergent bias. What caused the biased results?

AThe AI model was trained in winter and applied in summer.

BThe application was migrated from on-premise to a public cloud.

CThe team set flawed expectations when training the model.

DThe training data used was inaccurate.

Show Suggested Answer

Suggested Answer: B

Workflow design patterns for machine learning pipelines are common solutions to recurring problems in building and managing machine learning workflows. One of these patterns is to represent a pipeline with a directed acyclic graph (DAG), which is a graph that consists of nodes and edges, where each node represents a step or task in the pipeline, and each edge represents a dependency or order between the tasks. A DAG has no cycles, meaning there is no way to start at one node and return to it by following the edges. A DAG can help visualize and organize the pipeline, as well as facilitate parallel execution, fault tolerance, and reproducibility.

by Nada at Jul 14, 2024, 01:10 AM

Limited Time Offer

25%

Off

Get Premium AIP-210 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Sean

3 months ago

Isn't it possible that B played a role too?

upvoted 0 times

...

Marti

3 months ago

Definitely agree with D, bad data leads to bad results.

upvoted 0 times

...

Theola

4 months ago

Wait, how does training in winter affect summer sales?

upvoted 0 times

...

Ronny

4 months ago

I think C could also be a big factor.

upvoted 0 times

...

Lorenza

4 months ago

Sounds like D is the main issue here.

upvoted 0 times

...

Annette

4 months ago

I’m a bit confused about the cloud migration part. I don’t see how that would directly cause bias, but I guess it could affect data handling. Maybe option B is less likely?

upvoted 0 times

...

Demetra

5 months ago

I feel like I’ve seen a question similar to this before, and it was about seasonal trends affecting sales predictions. So, option A might be relevant here.

upvoted 0 times

...

Karina

5 months ago

I’m not entirely sure, but I think if the expectations set during training were unrealistic, it could lead to biased results. That makes me lean towards option C.

upvoted 0 times

...

Lezlie

5 months ago

I remember discussing how training data can really impact model performance, so I think option D about inaccurate training data could be the cause of bias.

upvoted 0 times

...

Tiffiny

5 months ago

I've seen issues with training data quality causing bias before. That's my best guess for the cause in this case, but I'll double-check the other options just to be sure.

upvoted 0 times

...

Tamra

5 months ago

Hmm, I'm a bit confused about what "emergent bias" means in this context. I'll need to think through the potential causes carefully.

upvoted 0 times

...

Leatha

5 months ago

This question seems straightforward, but I want to make sure I understand the key details before answering.

upvoted 0 times

...

Christa

5 months ago

Okay, I think the key here is to identify what could have led to biased results in the training data. I'll review the options and see which one seems most likely.

upvoted 0 times

...

Alyce

5 months ago

Hmm, this one's tricky. I'll have to think it through carefully.

upvoted 0 times

...

Cherelle

5 months ago

Hmm, I'm a bit unsure about this one. The question mentions HTML tags that are not XHTML-compliant, so I'll need to think carefully about which XHTML doctype would be most appropriate.

upvoted 0 times

...

Helaine

5 months ago

Hmm, I'm not sure about this one. I was thinking the RMSE might give me a sense of the overall error, but I'm not sure if that would tell me the direction of the error.

upvoted 0 times

...

Dottie

10 months ago

I'm going to have to go with C. Flawed expectations? Sounds like the team was playing a game of 'Guess the Bias' instead of 'Predict the Sales'.

upvoted 0 times

Nguyet

9 months ago

C) The team set flawed expectations when training the model.

upvoted 0 times

...

Jenelle

9 months ago

B) The application was migrated from on-premise to a public cloud.

upvoted 0 times

...

Bettyann

10 months ago

A) The AI model was trained in winter and applied in summer.

upvoted 0 times

...

Kelvin

10 months ago

Nah, I'm sticking with option A. Training in winter and applying in summer? That's a recipe for disaster. Looks like the team needed to invest in a seasonal wardrobe for their AI model.

upvoted 0 times

...

Janessa

10 months ago

Oh, I'm feeling lucky with B. Migrating to the cloud? That's bound to introduce all kinds of unexpected biases. Gotta love technology, am I right?

upvoted 0 times

Kattie

9 months ago

C) The team set flawed expectations when training the model.

upvoted 0 times

...

Lashonda

9 months ago

Oh, I'm feeling lucky with B. Migrating to the cloud? That's bound to introduce all kinds of unexpected biases. Gotta love technology, am I right?

upvoted 0 times

...

Garry

9 months ago

B) The application was migrated from on-premise to a public cloud.

upvoted 0 times

...

Brandon

10 months ago

A) The AI model was trained in winter and applied in summer.

upvoted 0 times

...

Lashanda

11 months ago

I don't know, D seems like the obvious choice to me. Inaccurate training data is a surefire way to get biased predictions. Maybe the team should have used a crystal ball instead?

upvoted 0 times

...