- A
The prediction field is not a binary field
Why wrong: The field is binary (true/false) as stated.
- B
The data is imbalanced favoring the negative class
Imbalanced data causes the model to predict majority class most of the time, yielding high accuracy but low positive precision.
- C
The prediction score field is not configured correctly
Why wrong: Prediction score field configuration does not affect model training accuracy/precision.
- D
The dataset is too small for training
Why wrong: Small dataset may cause overfitting, but the described symptoms point to class imbalance.
Question 887 of 1,000
Why Your Einstein Prediction Builder Model Has High Accuracy but Low Precision
This AI Associate practice question tests your understanding of salesforce einstein ai features. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A company uses Einstein Prediction Builder to predict which leads will convert. They have a binary outcome field 'Converted__c' which is true for 8% of leads. After training, the model shows high accuracy (95%) but very low precision for the positive class. What is the most likely cause?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue:
"most likely"Why it matters: Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
The data is imbalanced favoring the negative class
Option B is correct because the dataset is imbalanced: only 8% of leads are positive (Converted__c = true), while 92% are negative. In such a scenario, a model can achieve 95% accuracy by simply predicting the majority class (negative) for all leads, but this yields very low precision for the positive class because it rarely predicts positive correctly. Einstein Prediction Builder, like most ML models, is sensitive to class imbalance, and without techniques like oversampling or threshold tuning, the model will favor the majority class.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The prediction field is not a binary field
Why it's wrong here
The field is binary (true/false) as stated.
- ✓
The data is imbalanced favoring the negative class
Why this is correct
Imbalanced data causes the model to predict majority class most of the time, yielding high accuracy but low positive precision.
Clue confirmation
The clue word "most likely" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
The prediction score field is not configured correctly
Why it's wrong here
Prediction score field configuration does not affect model training accuracy/precision.
- ✗
The dataset is too small for training
Why it's wrong here
Small dataset may cause overfitting, but the described symptoms point to class imbalance.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates see 'high accuracy' and assume the model is performing well, overlooking that accuracy is misleading in imbalanced datasets, and they may incorrectly attribute the issue to field configuration or dataset size.
Detailed technical explanation
How to think about this question
Under the hood, Einstein Prediction Builder uses automated machine learning (AutoML) with algorithms like gradient boosting or logistic regression. When data is imbalanced, the model's loss function optimizes for overall accuracy, leading to a decision boundary that heavily favors the majority class. A real-world scenario is fraud detection, where fraudulent transactions are rare (e.g., 1%), and a model with 99% accuracy might miss all fraud cases, resulting in near-zero precision for the positive class. Techniques like class weighting, SMOTE, or adjusting the prediction threshold are required to improve precision.
KKey Concepts to Remember
- Read the scenario before looking for a memorised answer.
- Find the constraint that changes the correct option.
- Eliminate answers that are true in general but not in this case.
TExam Day Tips
- Watch for words such as best, first, most likely and least administrative effort.
- Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A practitioner preparing for the AI Associate exam encounters this exact type of scenario on the job. The correct answer here is not the most general option — it is the best answer for the specific constraint described. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Real exam questions reward reading the full scenario before eliminating options, because the constraint defines which answer fits.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
Salesforce Einstein AI Features — study guide chapter
Learn the concepts, then practise the questions
- →
Salesforce Einstein AI Features practice questions
Targeted practice on this topic area only
- →
All AI Associate questions
1,000 questions across all exam domains
- →
Salesforce AI Associate AI Associate study guide
Full concept coverage aligned to exam objectives
- →
AI Associate practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related AI Associate practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Ethical AI and Data Privacy practice questions
Practise AI Associate questions linked to Ethical AI and Data Privacy.
Salesforce Einstein AI Features practice questions
Practise AI Associate questions linked to Salesforce Einstein AI Features.
AI Fundamentals practice questions
Practise AI Associate questions linked to AI Fundamentals.
AI Capabilities in CRM practice questions
Practise AI Associate questions linked to AI Capabilities in CRM.
Ethical Considerations of AI practice questions
Practise AI Associate questions linked to Ethical Considerations of AI.
Data for AI practice questions
Practise AI Associate questions linked to Data for AI.
AI Associate fundamentals practice questions
Practise AI Associate questions linked to AI Associate fundamentals.
AI Associate scenario practice questions
Practise AI Associate questions linked to AI Associate scenario.
AI Associate troubleshooting practice questions
Practise AI Associate questions linked to AI Associate troubleshooting.
Practice this exam
Start a free AI Associate practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this AI Associate question test?
Salesforce Einstein AI Features — This question tests Salesforce Einstein AI Features — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: The data is imbalanced favoring the negative class — Option B is correct because the dataset is imbalanced: only 8% of leads are positive (Converted__c = true), while 92% are negative. In such a scenario, a model can achieve 95% accuracy by simply predicting the majority class (negative) for all leads, but this yields very low precision for the positive class because it rarely predicts positive correctly. Einstein Prediction Builder, like most ML models, is sensitive to class imbalance, and without techniques like oversampling or threshold tuning, the model will favor the majority class.
What should I do if I get this AI Associate question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Are there clue words in this question I should notice?
Yes — watch for: "most likely". Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more ways this is tested on AI Associate
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A healthcare company uses Einstein Prediction Builder to predict patient no-shows. After training a model, they receive a low prediction accuracy. Which THREE actions should they take to improve?
hard- ✓ A.Increase the number of records in the training dataset
- B.Use Einstein Discovery instead
- ✓ C.Change the prediction field to a different field
- D.Enable Einstein Case Classification
- ✓ E.Add more relevant features (input fields) to the dataset
Why A: Increasing the number of records in the training dataset helps the model learn more patterns and reduces overfitting, which directly improves prediction accuracy. Einstein Prediction Builder requires a minimum number of historical records to produce statistically significant results, and more data generally leads to better model performance.
Keep practising
More AI Associate practice questions
- An admin wants to compare the AI-generated forecast with a rep's commit forecast to identify gaps. Which feature should…
- A Salesforce admin implements Einstein Bots for customer service. To ensure the bot does not use biased language, what s…
- Which Einstein feature provides automated statistical analysis of Salesforce data, including story creation and improvem…
- A sales operations team wants to improve forecast accuracy by using AI. They currently use manual rollups. Which TWO Ein…
- A sales rep wants to generate a personalized email to a prospect using AI. Which Einstein GPT feature should they use?
- A healthcare company uses Einstein Prediction Builder to predict patient no-shows. After training a model, they receive…
Last reviewed: Jul 4, 2026
This AI Associate practice question is part of Courseiva's free Salesforce certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI Associate exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.