← Experian Interview Insights

Experian·Data Scientist·Online Assessment (OA)·Intermediate

Intermediate
May 2026

Summary

Experian DataLabs online assessment for a Data Scientist role, focused almost entirely on probability fundamentals. Four problems back to back, nothing too wild, but the pacing was quick enough that you had to recall formulas cleanly without much time to think.

Questions Asked (4)

Q1

You flip a fair coin repeatedly until you've gotten two heads total (not necessarily in a row). What is the expected number of flips?

Algorithms & Data Structures
Author's notes

This is the one I second-guessed myself on.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Use linearity of expectation by decomposing the process into two stages: waiting for the first head and then waiting for the second head. Recognize that each stage follows a geometric distribution with success probability 1/2, so the expected number of flips per stage is 2, giving a total of 4. Alternatively, model the process as a Markov chain or use negative binomial distribution to confirm the result.

Pro tip: Explicitly state that the expectation is 4 and then briefly justify why the memoryless property of the geometric distribution makes the second stage identical to the first. This shows you understand the underlying probabilistic structure and can communicate it clearly.

1. Define the random variable

Let X be the total number of flips needed to get two heads. Break X into X1 (flips to get first head) and X2 (additional flips to get second head after the first).

2. Identify distributions

Recognize that X1 and X2 are independent and each follows a geometric distribution with success probability p = 1/2, so E[X1] = E[X2] = 1/p = 2.

3. Apply linearity of expectation

Since X = X1 + X2, the expected total flips is E[X] = E[X1] + E[X2] = 2 + 2 = 4.

4. Verify with alternative method (optional)

If time permits, mention that the negative binomial distribution gives the same result: expected flips for r=2 successes is r/p = 2/(1/2) = 4.

Key Points to Mention

  • Linearity of expectation allows breaking the problem into simpler stages.
  • Geometric distribution models the number of trials until the first success, with mean 1/p.
  • The memoryless property ensures the second stage is independent and identical to the first.
  • The negative binomial distribution generalizes this to r successes, with mean r/p.
  • The final answer is 4 flips.
  • Avoid overcomplicating; a clear, step-by-step probabilistic reasoning is sufficient.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q2

If you flip a fair coin three times, what is the probability of getting exactly two heads?

Algorithms & Data Structures
Author's notes

Straightforward binomial.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clearly defining the sample space for three fair coin flips, then count the number of outcomes with exactly two heads. Use the binomial probability formula to compute the probability, and explain each step to show your reasoning.

Pro tip: After giving the answer, briefly mention how this simple calculation generalizes to the binomial distribution, which is fundamental in many data science applications such as A/B testing and classification. This shows you can connect basic probability to practical data science work.

1. Define the experiment and sample space

State that each flip has two equally likely outcomes (H or T), and for three flips there are 2^3 = 8 possible sequences. List them if helpful.

2. Identify favorable outcomes

Count the sequences with exactly two heads: HHT, HTH, THH. There are 3 such outcomes.

3. Compute probability using counting

Divide the number of favorable outcomes by the total number of outcomes: 3/8 = 0.375.

4. Verify with binomial formula

Use the binomial probability formula: P(X=2) = C(3,2) * (0.5)^2 * (0.5)^1 = 3 * 0.25 * 0.5 = 0.375, confirming the result.

5. Interpret and generalize

Explain that the probability is 37.5%, and note that this is a specific case of the binomial distribution with n=3, p=0.5.

Key Points to Mention

  • Sample space of 8 equally likely outcomes for three fair coin flips
  • Favorable outcomes: exactly two heads (HHT, HTH, THH)
  • Probability = favorable / total = 3/8 = 0.375 or 37.5%
  • Binomial distribution formula: P(X=k) = C(n,k) * p^k * (1-p)^(n-k)
  • Independence of coin flips and fair coin assumption (p=0.5)
  • Connection to broader data science concepts like binomial tests and A/B testing

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q3

P(A) = 0.3, P(B) = 0.5, P(A and B) = 0.15. What is P(A | B)?

Algorithms & Data Structures
Author's notes

P(A|B) = 0.15 / 0.5 = 0.3.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

State the definition of conditional probability: P(A|B) = P(A and B) / P(B). Plug in the given values and compute the result. Then briefly interpret the result in the context of the problem.

Pro tip: After computing, mention that P(A|B) = 0.3 equals P(A), indicating independence. This shows deeper understanding and connects to real-world data science scenarios.

1. Recall the formula

Write down the definition of conditional probability: P(A|B) = P(A ∩ B) / P(B), assuming P(B) > 0.

2. Substitute given values

Plug in P(A ∩ B) = 0.15 and P(B) = 0.5 into the formula.

3. Compute the result

Perform the division: 0.15 / 0.5 = 0.3.

4. Interpret the result

Note that P(A|B) = 0.3, which equals P(A). This suggests that A and B are independent events.

Key Points to Mention

  • Definition of conditional probability: P(A|B) = P(A and B) / P(B)
  • Calculation: 0.15 / 0.5 = 0.3
  • Interpretation: P(A|B) = P(A), indicating independence
  • Assumption that P(B) > 0
  • Connection to independence: P(A and B) = P(A) * P(B) if independent
  • Relevance to data science: conditional probability is fundamental in Bayesian inference and predictive modeling

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q4

P(A) = 0.3, P(B) = 0.4, P(A and B) = 0.12. What is P(A | B)?

Algorithms & Data Structures
Author's notes

Same formula, P(A|B) = 0.12 / 0.4 = 0.3.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Recognize that this is a straightforward application of the definition of conditional probability: P(A|B) = P(A and B) / P(B). Plug in the given values and compute the result, then briefly interpret what it means in context.

Pro tip: After computing the numerical answer, mention that since P(A|B) = P(A) = 0.3, events A and B are independent. This demonstrates deeper understanding and connects to real-world data science scenarios like feature independence in Naive Bayes.

1. Identify the formula

Recall the definition of conditional probability: P(A|B) = P(A and B) / P(B), provided P(B) > 0.

2. Plug in the given values

Substitute P(A and B) = 0.12 and P(B) = 0.4 into the formula: P(A|B) = 0.12 / 0.4.

3. Compute the result

Perform the division: 0.12 ÷ 0.4 = 0.3. So P(A|B) = 0.3.

4. Interpret the result

Note that P(A|B) equals P(A) = 0.3, which indicates that A and B are independent events. This means knowing B occurred does not change the probability of A.

Key Points to Mention

  • Definition of conditional probability: P(A|B) = P(A and B) / P(B)
  • Calculation: 0.12 / 0.4 = 0.3
  • Independence check: P(A|B) = P(A) implies independence
  • Real-world relevance: conditional probability is fundamental in Bayesian inference, Naive Bayes, and many data science applications
  • Assumption: P(B) > 0, which holds here since P(B) = 0.4
  • Potential pitfall: confusing P(A|B) with P(B|A) or P(A and B)

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.