Boston Consulting Group Data Scientist interview questions

26 Data Scientists have shared notes from their Boston Consulting Group interviews, with the questions they were asked in each round. That is 87% of the 30 Boston Consulting Group interview notes on Screna AI.

26 Data Scientist interview notes

Boston Consulting Group·Data Scientist·Take-home Assignment

Jul 2026
BCG data scientist round that was basically a full ML pipeline exercise. One meaty question covering everything from train/test splits to gradient boosting to generalization techniques. Felt more like a take-home than a live interview.
  • Given a cleaned retail dataset, split it 80/20 with stratification on the target, build a reproducible preprocessing pipeline (standardize numerics, one-hot encode categoricals), train a gradient-boosted tree model, report AUC on the test set, and describe two techniques you'd use to improve generalization if AUC comes out low.

“This was a lot bundled into one question.”

View Post

Boston Consulting Group·Data Scientist·Technical Phone Screen

Jul 2026
Interviewed for a Data Scientist role at BCG and got hit with a probability question that felt more like a stats exam than a job interview. Not a bad experience, just a bit academic.
  • You roll a fair six-sided die 10 times. What is the probability of getting exactly 3 sixes? Also, what are the expected number and standard deviation of sixes across those 10 rolls?

“I knew it was binomial the second they said 'exactly 3' but I fumbled the standard deviation formula for a moment.”

View Post

Boston Consulting Group·Data Scientist·Technical Phone Screen

Jul 2026
BCG data scientist technical screen, basically one long pandas problem that covers data cleaning, merging, and aggregation all at once. Pretty dense for a single question but it tells you exactly what they care about.
  • Given two user and event DataFrames with messy currency strings, misaligned columns, and mixed schemas, use pandas (no loops) to clean and combine everything, then compute per country and plan metrics for a specific date: distinct active users, purchasers, purchase counts, and revenue. Return a sorted tidy DataFrame and explain your assumptions about nulls and timezones.

“This took me longer to mentally parse than I expected.”

View Post

Boston Consulting Group·Data Scientist·Take-home Assignment

Jul 2026
BCG data scientist take-home that was basically one enormous pandas question disguised as five smaller ones. The scope was way bigger than I expected for a single problem, and I spent way too long on the dedup and timezone normalization pieces before I even got to the feature engineering.
  • Given two CSVs with transaction and user data, write production-ready pandas code (no groupby.apply, no row-level loops, must scale to 100M+ rows) to: parse and UTC-normalize timestamps, deduplicate transactions by keeping the row with the latest updated_at per txn_id, and drop rows with invalid amounts, invalid transaction types, or timestamps outside a defined range.
  • Separate refunds and chargebacks from purchase transactions, define net_spend as the sum of purchase amounts only, and retain a flag indicating whether any refunds or chargebacks exist per user.
  • Build month-level features per user for a five-month window, where months are defined in the user's local timezone but aggregated after converting to UTC. Features include: active_month (binary), monthly_net_spend, and a rolling 3-month median spend computed only over active months (no zero-filling for inactive months).
  • For each user-month, identify the top 3 merchant categories by net spend, with ties broken first by spend then lexicographically by category name, and output them as cat1, cat2, cat3 columns. Fill with 'None' if fewer than 3 categories exist.
  • Produce a single-row-per-user snapshot as of 2024-07-31 with columns for months active in the last 5 months, total net spend, a refund/chargeback flag, rolling 3-month median spend at snapshot date, and the top-3 merchant categories for July 2024. The pipeline must be idempotent and memory-efficient.

“The dedup part sounds trivial until you realize there are near-duplicate rows sharing the same txn_id and dup_hint but different updated_at values.”

View Post

Boston Consulting Group·Data Scientist·Technical Phone Screen

Jun 2026
BCG data scientist technical screen, one big multi-part question about loss functions for regression. Dense enough that I left unsure if I'd actually nailed it or just sounded like I knew what I was talking about.
  • You're building a regression model to predict car prices in USD with an unscaled target. Walk through when and why you'd choose MSE over MAE, covering optimization behavior, convexity, outlier sensitivity, probabilistic assumptions, business fit, and how leaving the target unscaled affects training.

“This was basically six questions duct-taped together and they just...”

View Post

Boston Consulting Group·Data Scientist·Take-home Assignment

Jun 2026
BCG data scientist take-home, basically one giant multi-part problem covering the full ML pipeline from temporal splitting to production deployment. Pretty dense for a single assignment and felt more like a work sample than an interview.
  • Build a reproducible training pipeline for a severely imbalanced binary classification dataset (1% positive rate) that uses temporal train/val/test splits, applies standardization and one-hot encoding, handles class imbalance inside CV folds without leaking validation data, trains a strong baseline, and outputs calibrated probabilities.
  • Report ROC-AUC and PR-AUC on the test split, recall at 5% FPR, and the decision threshold that maximizes F1 subject to recall being at least 0.90.
  • How would you choose the operating point for a production system with a hard constraint of at most 2 false positives per 1,000 predictions?
  • How might model calibration drift over time, and what technique would you use to monitor and re-calibrate without leaking future labels?

“This was the bulk of the work.”

View Post

Boston Consulting Group·Data Scientist·Online Assessment (OA)

Jun 2026
BCG CodeSignal notebook assessment for a Data Scientist role, one question involving pandas and some annoying schema mismatch between two CSV files. Pretty straightforward if you've done any data wrangling before, but the column name typo is the kind of thing that bites you if you're moving fast.
  • Given two CSV files of order data from different years with inconsistent column names, use pandas to load both files, standardize the column names to a common schema, cast the amount column to float, and concatenate them into a single DataFrame.

“The actual pandas steps are not the hard part.”

View Post

Boston Consulting Group·Data Scientist·Online Assessment (OA)

Jun 2026
BCG Data Scientist case interview, timed online format. You get a fashion company profit decline scenario, work through exhibits, and then record a one-minute video summary for a fake executive audience. The video part is the part nobody warns you about.
  • A fashion company's profits have dropped. Using the provided exhibits, identify the main drivers of the decline (price, volume, mix, cost, or some combination) and propose two or three concrete, data-backed initiatives to turn things around.
  • Record a 60-second video executive summary of your findings and recommendations, as if presenting to senior leadership.

“The exhibits do most of the heavy lifting if you read them carefully, but I wasted time trying to be clever instead of just quantifying what was obviously the biggest driver first.”

View Post

Boston Consulting Group·Data Scientist·Online Assessment (OA)

Jun 2026
BCG data science online assessment, notebook-style coding environment. One question on feature scaling that sounds mechanical until they ask you to justify your choices.
  • You have a DataFrame with numeric columns for age and income. Apply standard scaling to age and min-max normalization to income, then explain when you'd choose one approach over the other.

“The code part was fine, sklearn makes it pretty straightforward.”

View Post

Boston Consulting Group·Data Scientist·Technical Phone Screen

Jun 2026
BCG data scientist interview that was basically one long technical problem about deploying a classifier on a heavily imbalanced dataset. The whole thing revolved around precision constraints and threshold selection, with a side of 'write the code too.' Pretty intense for what felt like a single question.
  • You have an imbalanced dataset with about 5% positive class. The product team requires test-set precision of at least 0.95 on the positive class. Walk through how you'd train a probabilistic model, find the right classification threshold on validation data, and then evaluate on the held-out test set. Report precision, recall, predicted positive count, and expected false positives if you flag 1,000 items.
  • If no threshold on the validation set can achieve 0.95 precision, what are two concrete strategies you'd propose, and what are the risks of each?
  • Write sklearn-style code to search for the optimal threshold using precision_recall_curve or a custom scorer, without leaking test data into the selection process.
  • How does class imbalance affect calibration, and why is optimizing ROC AUC a misleading objective when you have a hard precision constraint?

“This was the core of the whole interview.”

View Post