What is the least operational overhead way to calculate simple probability for an educational game?

Machine Learning vs. Traditional Programming / AIF-C01

A company wants to develop an educational game where users answer questions such as the following: "A jar contains six red, four green, and three yellow marbles. What is the probability of choosing a green marble from the jar?" Which solution meets these requirements with the LEAST operational overhead?

Use supervised learning to create a regression model that will predict probability.
Use reinforcement learning to train a model to return the probability.
Use code that will calculate probability by using simple rules and computations. Source Reference Answer
Use unsupervised learning to create a model that will estimate probability density.

Community Votes

100%

100% of anonymous learners picked answer C. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

The exam tests whether you can recognize when a rule-based computation is better than ML; the trap is assuming all probability problems need a model.

For a simple probability question like marbles, ML models are overkill; direct code calculation is simplest. Community consensus strongly supports option C as the minimal-operational-overhead solution.

Choosing A or D because they involve models that can output probabilities, ignoring the unnecessary training, data, and deployment overhead.

Community Discussion (6 comments)

aswathsaikarthick 👍 2 Selected: C

Estimated Costs Memory: Less than 1 MB for the model. Computation: A few seconds to minutes on a standard laptop CPU. Data: A few hundred examples, which can be generated programmatically. Instead def calculate_probability(green_marbles, total_marbles): return green_marbles / total_marbles # Example usage green_marbles = 4 total_marbles = 6 + 4 + 3 # red + green + yellow probability = calculate_probability(green_marbles, total_marbles) print(f"Probability of choosing a green marble: {probability:.2f}") A program is effective and time saving

Jessiii 👍 1 Selected: C

The problem described is a simple probability calculation based on basic combinatorics. The probability of choosing a green marble is simply the ratio of green marbles to total marbles, which can be computed directly without needing a complex machine learning model. Using a straightforward code implementation to calculate the probability based on the given numbers (6 red, 4 green, and 3 yellow marbles) will be the most efficient and have the least operational overhead. It’s a direct computation using basic arithmetic.

afrazkhan 👍 3 Selected: C

no NEED to do do anything fancy. its doable with simple code

Moon 👍 4 Selected: C

C: Use code that will calculate probability by using simple rules and computations. Explanation: For a question like this, where the probability can be computed using basic arithmetic (e.g., number of favorable outcomes divided by total outcomes), implementing a straightforward function in code will meet the requirements with the least operational overhead. This avoids the complexity and resource demands of machine learning. For example: Total marbles = 6 + 4 + 3 = 13 6+4+3=13

jove 👍 4 Selected: C

Make it simple : Use code that will calculate probability by using simple rules and computations.

tccusa 👍 3 Selected: C

Not necessary to train a model for this. Code for computation is sufficient.

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Expert Analysis

Why the Answer Is Correct

The probability of drawing a green marble is deterministic arithmetic: 4 green marbles divided by 13 total marbles. A simple function with rules and computations solves it exactly and immediately, with no training data, no model deployment, and no ongoing maintenance. This aligns with AWS Well-Architected principle of minimizing operational overhead.

Why the Other Options Are Wrong

Option A (supervised regression) requires historical data and model training to approximate a value that can be computed directly, adding cost and complexity. Option B (reinforcement learning) is designed for sequential decision-making and rewards, not for one-shot arithmetic probability. Option D (unsupervised density estimation) is used to model underlying distributions from data; it would require data, training, and interpretation, which is far more overhead than simple division.

Community Comment Notes

The commenters consistently favored C, with one noting 'no NEED to do anything fancy' and another pointing out the problem 'can be computed using basic arithmetic.' A detailed comment even provided a custom Python function: def calculate_probability(green_marbles, total_marbles): return green_marbles / total_marbles. Several others reinforced that training a model is unnecessary when simple code suffices.

Official Reference

Exam Strategy

When an answer choice proposes ML, ask whether the problem is deterministic and can be solved with simple logic. If the input is finite and the formula is known, direct code always has lower operational overhead than training and deploying a model.

Related Analysis

Practice All AIF-C01 Questions

Access 100 questions with complete answers and detailed explanations.

View Full AIF-C01 Practice Test →

← Back to AIF-C01 Study Guide