Coinbase Data Scientist Interview Questions

Coinbase·Data Scientist·Online Assessment (OA)

Jul 2026

Coinbase Data Scientist aptitude screen, the timed kind where you have 50 questions and 15 minutes and basically have to triage on the fly. Mix of number sequences, pattern recognition, and grammar. Nothing conceptually hard but the clock is the whole challenge.

What is the next number in the sequence 3, 6, 12, 24, ___?
A repeating symbol pattern (triangle, square, circle) cycles in order. Which symbol appears in the 10th position?
Fill in the blank: 'She postponed the launch because she ____ the data were incomplete.' Choose the correct verb form from the options given.

“Each term doubles.”

View Post

Coinbase·Data Scientist·Onsite - Product Sense / Strategy

Jul 2026

Coinbase DS interview with two meaty case questions back to back, one on campaign measurement and one on whether to list a new trading pair. No fluff, just open-ended frameworks with a lot of moving parts. Felt like a take-home that got turned into a live conversation.

You ran a 4-week paid marketing campaign across multiple channels. How would you evaluate whether it succeeded?
How would you compare campaign performance fairly across channels like Search, Social, and Affiliates?
What guardrail metrics would you watch during a marketing campaign, and why?
Product wants to list a new trading pair. Walk me through how you'd decide whether to launch it.
How would you evaluate liquidity and market quality for a newly listed trading pair?
After launching a new trading pair, what metrics would define success and how would you monitor them?

“I started with incremental funded accounts as the primary metric because raw signups are too easy to game and revenue takes too long to materialize in a 4-week window.”

View Post

Coinbase·Data Scientist·Technical Phone Screen

Jul 2026

Coinbase data science interview with a product estimation question built around a real marketing scenario. Pretty open-ended, which I wasn't fully prepared for.

A crypto company runs a Super Bowl ad showing only a QR code. Viewers who scan it and complete sign-up get a $15 coupon. Estimate the total number of successful sign-ups from that campaign.

“I started with Super Bowl viewership, which felt solid ground, then immediately got tangled trying to estimate scan rates because I kept second-guessing myself on how many people actually have their phone out while watching.”

View Post

Coinbase·Data Scientist·Technical Phone Screen

Jul 2026

This was a deep-dive technical screen for a DS role at Coinbase, basically a full experiment design case with a debugging twist. The questions were meaty and required actual math, not just framework recitation. Left feeling like I'd run a marathon.

Define a precise primary metric and two to three guardrail metrics for a personalized product email experiment. Assume intent-to-treat with user-level randomization, and explain how you'd handle eligibility rules and users who receive multiple emails.
Given a baseline 7-day purchase conversion of 3.5%, calculate the sample size needed to detect a 10% relative lift at two-sided alpha 0.05 and 80% power with a 1:1 split. With 500,000 eligible users per day and 85% deliverability, how many calendar days does the test need to run including the full attribution window?
Now power the same experiment for 7-day revenue per randomized user instead of conversion rate. Mean is $0.90, SD is $12.00, and you want to detect a $0.10 absolute lift. What per-arm sample size and run length does that imply?
Compute the two-proportion z-test p-value and 95% confidence interval for each of the two experiment runs separately, then compute a fixed-effects meta-analytic pooled estimate across both. Based on that, should the team launch?
List at least six plausible reasons why the first and second experiment runs produced such different results. For each, describe the specific data checks or queries you'd run to investigate.
Propose a full re-analysis plan covering pre-registration, covariate adjustment, heterogeneity of treatment effects, sequential monitoring corrections, and a holdout strategy for ramp. What decisions would you make if the pooled lift lands between zero and five percent?

“I fumbled the multi-email part initially.”

View Post

Coinbase·Data Scientist·Technical Phone Screen

Jul 2026

Coinbase data scientist interview that dropped a full end-to-end modeling exercise on me with no warm-up. You're basically doing a live analysis from raw data to model evaluation to recommendations, all on the spot. Pretty intense if you're not used to thinking out loud under pressure.

Given a raw behavioral dataset, walk through your full analysis pipeline: clean the data, explore it, build a model to predict conversion, evaluate it, and propose improvements.

“This was basically the whole interview compressed into one question.”

View Post

Coinbase·Data Scientist·Technical Phone Screen

Jul 2026

Coinbase data science interview with a product analytics case built around a Super Bowl QR code campaign. The whole thing was funnel estimation, which sounds straightforward until you're actually in it trying to justify every assumption out loud.

Given a TV network airs a QR code ad during the Super Bowl, how would you estimate the percentage of viewers who actually scan the code?
What data sources would you draw on to support this kind of scan rate estimate?
If you only have prior TV campaign data and no ad-partner conversion data, how do you approximate the scan rate?
How would you estimate the conversion rate from someone scanning the QR code to completing an account sign-up?

“I went straight to viewership numbers and tried to layer in attention decay, second-screen behavior, that kind of thing.”

View Post

Coinbase·Data Scientist·Technical Phone Screen

Jul 2026

Coinbase data scientist interview with a scenario-based question about diagnosing a metric anomaly in the wallet product. One question, but it had a lot of layers to it.

If you noticed an unusual change in engagement or a key metric for Coinbase Wallet, how would you structure your investigation? What hypotheses would you form, and what data would you use to confirm or rule each one out?

“This is one of those questions where the answer lives in how you organize your thinking, not in any single clever insight.”

View Post

Coinbase·Data Scientist·Technical Phone Screen

Jul 2026

Interviewed for a Data Scientist role on the Identity & Trust team at Coinbase. The whole thing was essentially one long experiment design question with a lot of moving parts, and I left feeling like I'd covered maybe 70% of what they were actually looking for.

How would you design an A/B test to evaluate the launch of an identity verification feature with trust signals like verified badges and suspicious profile warnings? Walk through randomization, metrics, rare event measurement, network effects, bias sources, and how you'd interpret mixed results.

“This was basically a gauntlet.”

View Post

Coinbase·Data Scientist·Technical Phone Screen

Jul 2026

SQL-heavy technical screen for a DS role at Coinbase. Three questions, all back-to-back, all on the same invented schema. No behavioral stuff at all which surprised me, just pure query writing under time pressure.

Given a users table and a transactions table, write SQL to compute adoption rate and transaction rate per region for August 2025. Adoption rate is the share of users in that region who adopted in August, transaction rate is the share who made at least one transaction in August.
For each user, calculate the number of days between their adoption date and their first transaction. Only include users where adopted_at is not null and the first transaction happened after adoption. Then write a second query returning the p10, p50, and p90 of that value.
Define a cross-region sale as any transaction where the transaction region differs from the user's earliest-ever transaction region. Write a query that returns all August 2025 transactions with a flag indicating whether each is a cross-region sale, plus the user's first transaction region.

“Took me longer than it should have to realize I needed to keep all users in the denominator, not just the ones with activity.”

View Post

Coinbase·Data Scientist·Technical Phone Screen

Jul 2026

Coinbase data science interview with two meaty case questions back to back. One was a classic estimation problem, the other a revenue diagnostics exercise. Nothing too exotic but the depth expected was real.

Estimate how many users would register on a platform after a Super Bowl ad airs. Walk through your funnel assumptions and justify each number.
Retail revenue has dropped. Walk through how you'd diagnose the problem and give specific example scenarios that could explain the decline.

“I started with total viewership and worked down through awareness, site visits, and finally registration conversion.”

View Post