The answer is that a field containing future information, such as 'churn_date', was included in the features. This is correct because it introduces target leakage, a specific form of data leakage in Einstein models where the model learns from data that would not be available at the time of prediction, causing inflated training accuracy but poor generalization to validation data. On the Salesforce AI Associate exam, this scenario tests your understanding of how future-leaning fields violate the core principle that features must be strictly historical or static to avoid data leakage in Einstein Discovery models. A common trap is mistaking this for overfitting, but the key distinction is that the model is not just memorizing noise—it is directly reading the answer from a future column. Memory tip: if a feature could only exist after the event you are predicting, it is a "time traveler" and must be removed.
AI Associate Data for AI Practice Question
This AI Associate practice question tests your understanding of data for ai. The scenario asks you to isolate a root cause — eliminate options that address a different problem before choosing. 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 data scientist notices that an Einstein model for predicting customer churn has unusually high accuracy on training data but performs poorly on validation data. Which data issue 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 the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
A field containing future information (e.g., 'churn_date') was included in features
Option D is correct because including a field like 'churn_date' in the feature set introduces target leakage, where the model has access to information that would not be available at prediction time. This causes the model to appear highly accurate on training data (since it can directly 'see' the outcome) but fails to generalize to validation data where such future information is absent. In Salesforce Einstein, features must be strictly historical or static to avoid this data leakage issue.
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 dataset has an imbalanced class distribution
Why it's wrong here
Imbalance typically causes poor recall on minority class, not a huge train/validation gap.
✗
The dataset contains many missing values
Why it's wrong here
Missing values often reduce overall performance, not specifically a gap.
✗
The model was trained on stale data from a different season
Why it's wrong here
Stale data would affect both sets similarly if validation is also outdated.
✓
A field containing future information (e.g., 'churn_date') was included in features
Why this is correct
Data leakage from a field that reveals the outcome causes overfitting and high train accuracy.
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.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Salesforce often tests the concept of data leakage by presenting it as a scenario where the model performs well on training data but poorly on validation data, and the trap is that candidates may confuse this with overfitting or class imbalance, rather than recognizing the inclusion of a future or target-related field as the root cause.
Trap categories for this question
Similar concept trap
Stale data would affect both sets similarly if validation is also outdated.
Detailed technical explanation
How to think about this question
Target leakage occurs when a feature includes information that is not available at the time of prediction, such as a future event or outcome. In Salesforce Einstein, the automated feature engineering pipeline can inadvertently include such fields if they are present in the dataset. A real-world scenario is including 'contract_end_date' when predicting churn, which directly reveals the churn outcome if the contract end is the churn event. The model learns to rely on this leaked signal, leading to perfect training accuracy but failing on new data where the field is absent or unknown.
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.
Data for AI — This question tests Data for AI — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: A field containing future information (e.g., 'churn_date') was included in features — Option D is correct because including a field like 'churn_date' in the feature set introduces target leakage, where the model has access to information that would not be available at prediction time. This causes the model to appear highly accurate on training data (since it can directly 'see' the outcome) but fails to generalize to validation data where such future information is absent. In Salesforce Einstein, features must be strictly historical or static to avoid this data leakage issue.
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 →
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.
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.