1D0-184 CIW AI Data Science Specialist Practice Questions
Prepare for 1D0-184 with more than an answer.
- Exam fee
- $175 USD
- Level
- Specialist
- Valid for
- 3 years
Domains covered on the exam 4
- Data Science Overview21%
- Analysis34%
- Managing Data17%
- Professional Skills28%
- 1
Case Study: TechFin Solutions
TechFin Solutions is implementing a new data warehouse to consolidate data from three sources: an internal SQL CRM, an external marketing API (JSON), and legacy flat files (CSV). The goal is to perform daily batch analytics.
During the initial design phase, the architect proposes using an Extract-Transform-Load (ETL) process. However, the data science team argues that they need access to the raw data for experimental modeling before any transformation rules are applied.
Which architecture modification BEST satisfies both the reporting needs and the data science team's requirements?
Show answer details
Correct answer: D
ELT (Extract-Load-Transform) loads raw data directly into a destination (like a Data Lake) before transformation. This allows the data science team to access raw data for experimentation while the data engineering team can build transformation pipelines from the lake to the warehouse for reporting.
- 2
Case Study: TechFin Solutions (Part 2)
Following the architecture decision, TechFin needs to handle the legacy flat files (CSV) which contain inconsistent date formats (e.g., 'MM/DD/YYYY' vs 'YYYY-MM-DD') and missing values in the 'Transaction_Amount' column.
Which sequence of Data Preparation steps is the MOST rigorous approach to prepare this specific data for a machine learning model?
Show answer details
Correct answer: C
This sequence addresses the specific issues: first, parsing and standardizing dates to make them usable; second, handling missing values (imputation is generally preferred over deletion for financial data to preserve record count); third, normalizing features to ensure the ML model treats them equally.
- 3
A data scientist is working with a dataset containing 100 features (variables). They suspect that many features are redundant or highly correlated, which is increasing computation time and risk of overfitting.
Which technique should be applied to reduce the number of variables while retaining the most variance in the data?
Show answer details
Correct answer: D
PCA is a dimensionality reduction technique that transforms a large set of variables into a smaller one that still contains most of the information (variance) in the large set.
- 4
A data science consultant is analyzing a dataset containing employee satisfaction scores (0-10) and annual attrition rates. The calculated Pearson correlation coefficient (r) between these two variables is -0.85.
Which statement accurately interprets this statistical result?
Show answer details
Correct answer: A
A Pearson correlation coefficient (r) of -0.85 indicates a strong negative linear relationship. The negative sign implies an inverse relationship (as one variable goes up, the other goes down), and the magnitude (0.85) is close to 1, indicating strength.
- 5
A retail company wants to implement a system that automatically identifies and flags fraudulent transactions in real-time without human intervention. The system must learn from new fraud patterns as they emerge daily.
Which terminology BEST describes the core technology required for this solution?
Show answer details
Correct answer: D
Machine Learning is the specific subset of AI defined by the ability of a system to learn from data and improve from experience (new fraud patterns) without being explicitly programmed for every specific rule.
- 6
A financial institution is building a credit scoring model. During testing, the team discovers the model consistently assigns lower credit scores to applicants from a specific zip code, despite income levels being equal to other regions.
Which ethical issue is demonstrated in this scenario?
Show answer details
Correct answer: C
This is a classic example of algorithmic bias, where the model has learned a prejudice (redlining) based on geographic features that proxy for protected characteristics, resulting in unfair outcomes for a specific group.
