American Express Machine Learning Interview Questions & Answers
Curated interview practice questions with answers. These are practice scenarios, not a verified list of past interview questions.
About American Express hiring for Machine Learning roles
American Express is a global payments and card company offering charge and credit cards, travel services and merchant acquiring. Its India centres in Gurugram and Bengaluru support technology, risk, analytics and servicing. It hires for software engineers, QA engineers, data analysts, data scientists and credit risk analysts.
For Machine Learning roles, this American Express practice set focuses most on MLOps and Deployment (6), Decision Trees and Ensembles (5), Data Preprocessing and Feature Engineering (4), Classification Models (4). It has 3 easy, 24 medium, 3 hard questions, so you can start easy and work up to the harder ones.
Company type
Banking & finance
Headquarters
New York, USA
Main India offices
Gurugram, Bengaluru
American Express Machine Learning interview process
Online assessment (aptitude + coding or analytics)
Technical round
Case or domain round
Hiring manager round
HR round
Typical pattern based on public candidate experiences. Rounds vary by role, team and year.
Solved for American ExpressStart practicing
3 QUESTIONS FREESign up to unlock the full question bank and track your progress.Unlock every question and answer, then continue practising company-wise and package-wise.
✓ 3 questions free • Unlock the rest in seconds
01
What makes XGBoost, LightGBM and CatBoost different?
XGBoost adds regularisation to the objective, uses second-order gradients and handles missing values natively. LightGBM grows trees leaf-wise and uses histogram binning, making it very fast on large data, though it can overfit small data. CatBoost handles categorical features with ordered target statistics and uses symmetric trees, giving strong defaults with less tuning. All three support GPU training.
02
What is one-hot encoding and when can it cause problems?
One-hot encoding turns a categorical column into binary columns, one per category, so models do not assume order. It causes problems with high-cardinality features like city or product ID, creating thousands of sparse columns and higher memory and overfitting risk. Alternatives are target encoding, frequency encoding, hashing, or grouping rare categories into 'Other'. Use handle_unknown='ignore' for unseen categories.
03
Your dataset has 800 correlated features and the model trains slowly. What would you do?
I would remove constant and near-duplicate features, drop one from each highly correlated pair, then apply PCA inside the pipeline and keep components explaining about 95 percent of variance. Alternatively, use L1-regularised models or tree importances for supervised selection. I would compare speed and cross-validated scores; often 50 to 100 features give nearly the same accuracy.
04
Compute permutation importance on validation data.
from sklearn.inspection import permutation_importance
import pandas as pd
r = permutation_importance(model, X_val, y_val, n_repeats=10,
scoring='roc_auc', random_state=42, n_jobs=-1)
imp = pd.Series(r.importances_mean, index=X_val.columns)
print(imp.sort_values(ascending=False))
Near-zero or negative values mean the feature adds little on unseen data.
05
Your house price model's residuals grow larger for expensive houses. What do you do?
That is heteroscedasticity, typical for price data that is right-skewed. I would model log(price) instead of price, which turns absolute errors into roughly percentage errors and stabilises variance. Then I would convert predictions back with exp and check residual plots again. Evaluating with RMSLE or MAPE also fits better when relative error matters more than absolute error.
06
Validation AUC is 0.99 on a loan default model. What do you suspect?
Such a high score on a hard problem usually signals leakage. I would check feature importances for a suspiciously dominant feature, look for fields recorded after the loan outcome such as collection status, verify preprocessing was fit only on training data, and check for duplicate customers across train and test. Then re-run with a time-based split to confirm a realistic score.
07
What is the difference between offline evaluation and online A/B testing of a model?
Offline evaluation measures metrics like AUC on historical holdout data; it is fast and cheap but cannot capture user behaviour changes or feedback loops. Online A/B testing exposes a share of real traffic to the new model and measures business outcomes like conversion or loss rate. Offline gains do not always translate online, so important models are validated with A/B tests or shadow deployments.
A model registry is a central store of model versions with metadata: training data version, parameters, metrics, owner and stage such as staging or production. It makes promotions and rollbacks controlled and auditable, and lets serving systems load a model by name and version. MLflow Model Registry, SageMaker Model Registry and Vertex AI Model Registry are common examples.
09
A model's accuracy dropped 10 percent over three months in production. How do you investigate?
I would first check data pipelines for broken features, nulls or schema changes, then compare current feature distributions with training data using PSI to find drift. I would check whether the label definition or business process changed, and analyse errors by segment. If drift is real, retrain on recent data, possibly with time-weighted samples, and set up automatic drift alerts and scheduled retraining.
from sklearn.ensemble import IsolationForest
iso = IsolationForest(n_estimators=300, contamination=0.01, random_state=42)
iso.fit(X_train)
scores = -iso.score_samples(X_new)
flags = iso.predict(X_new) == -1
Higher scores mean more anomalous. Tune contamination to match how many alerts reviewers can handle.
11
A new model has slightly better AUC but worse precision in the top 1,000 cases the team acts on. Which do you pick?
I would pick the model that does better where decisions are actually made. If the team only reviews the top 1,000 cases, precision at 1,000 or recall at that cut-off matters more than global AUC. I would make that the primary metric in future comparisons, and confirm the result holds across several time periods before switching.
12
A business stakeholder asks you to use deep learning for a 5,000-row tabular dataset. How do you respond?
I would explain that for small tabular data, gradient-boosted trees or regularised linear models usually match or beat neural networks, train faster and are easier to explain. I would propose building a simple baseline, then a boosting model, and only test a neural network if there is a clear reason. I would show the comparison on cross-validated metrics so the decision is data-driven.
13
How do one-vs-rest and multinomial approaches differ for multiclass classification?
One-vs-rest trains one binary classifier per class against all others and picks the highest score; it is simple but probabilities may not sum to one. Multinomial (softmax) logistic regression models all classes jointly with a single loss, giving consistent probabilities. For metrics, use macro averaging to treat classes equally or weighted averaging to account for class frequency.
14
Why do single decision trees overfit and how do you control it?
An unrestricted tree keeps splitting until leaves are pure, memorising noise. Control it with pre-pruning hyperparameters like max_depth, min_samples_split, min_samples_leaf and max_leaf_nodes, or with post-pruning through cost-complexity pruning using ccp_alpha. In practice ensembles such as random forests or boosting are used to reduce the variance of single trees.
15
You are asked to predict customer churn. How would you frame the ML problem from scratch?
First define churn precisely, for example no purchase in 60 days, and the prediction window. It becomes binary classification. Build features from data available before the cut-off date only, choose a time-based split, and pick metrics like recall at a fixed precision or lift in the top decile. Start with logistic regression as a baseline, then try boosting, and agree on how retention teams will use the scores.
16
The fraud team can only review 500 alerts a day. How do you set the threshold?
Instead of 0.5, rank transactions by predicted probability and pick the threshold that yields about 500 alerts per day on recent data. Then report precision and recall at that cut-off, or precision at k. I would monitor daily alert volume because drift can change it, and recompute the threshold periodically. If cost data exists, I would choose the threshold that maximises expected savings.
17
Your preprocessing works in notebooks but gives different results in production. Why?
Common causes are preprocessing written separately in two places, statistics like means recomputed on production data instead of using training values, different library versions, or different column order and data types. The fix is to save one fitted Pipeline with preprocessing and model together, pin versions, validate input schema, and test that the saved pipeline gives identical outputs on sample rows.
18
k-means gives one huge cluster and several tiny ones. What could be wrong?
Likely causes are unscaled features, where one large-range feature dominates distance; heavy skew or outliers pulling centroids; or data that is not naturally spherical. I would log-transform and scale features, remove or cap extreme outliers, and try different k values. If shapes are irregular, DBSCAN, HDBSCAN or a Gaussian Mixture Model may fit better.
19
What are overfitting and underfitting, and how do you detect them?
Overfitting is when a model memorises training noise and performs much worse on unseen data. Underfitting is when the model is too simple to capture the pattern, so both training and validation scores are poor. Detect them by comparing training and validation metrics or plotting learning curves. A large gap means overfitting; two low, close scores mean underfitting.
I would check the test first: enough sample size and duration, correct randomisation, and no bugs in serving such as stale features. Then investigate whether offline metrics really reflect user value, for example optimising clicks rather than purchases, or popularity bias. Segment-level analysis may show gains in some groups. I would revise the offline metric to better match the online goal.
22
How do you build a text classifier with TF-IDF and logistic regression?
Batch scoring runs on a schedule, for example nightly churn scores for all customers written to a table; it is simple, cheap and tolerant of slow models. Real-time inference returns predictions on request, such as fraud checks during payment, and needs low latency, high availability, scaling and fresh features. Choose real-time only when the decision must happen at the moment of the event.
Softmax turns a vector of raw scores into probabilities that sum to one: p_i = exp(z_i) / sum of exp(z_j). It is used in multinomial logistic regression and the output layer of neural networks for multiclass problems. Larger scores get exponentially larger shares. In practice the maximum score is subtracted before exponentiation to avoid numerical overflow.
25
When would you use AdaBoost and how does it re-weight samples?
AdaBoost trains weak learners, usually decision stumps, in sequence. After each round it increases the weights of misclassified samples so the next learner focuses on them, and gives each learner a vote weight based on its accuracy. It works well on clean data but is sensitive to noisy labels and outliers, which get ever larger weights. Gradient boosting is a generalisation that has largely replaced it.
26
A new model version performs badly right after release. How do you handle it?
Roll back immediately to the previous version from the model registry, which should be a one-step action. Then investigate: compare the input features served with those used in validation, check for training-serving skew, version mismatches or a wrong artifact. Add the failure case to automated pre-release checks, and use canary or shadow releases next time so issues affect only a small share of traffic.
27
Your random forest model file is 2 GB and too slow for real-time scoring. What can you do?
Reduce size by limiting max_depth and min_samples_leaf, using fewer trees since gains flatten after a few hundred, and dropping weak features. Alternatively switch to a gradient boosting model like LightGBM, which usually gives similar accuracy with far smaller, faster models. Converting to ONNX or using a compiled predictor can also speed up inference. Measure accuracy and latency after each change.
28
Two models have RMSE 120 and 125, but the second has much lower MAE. Which do you choose?
It depends on error cost. The first model makes fewer big errors, while the second is better on typical cases but has some large misses. If large errors are expensive, such as stock-outs of costly items, choose the first. If typical accuracy matters more, choose the second. I would also check error distributions by segment and discuss with stakeholders before deciding.
29
Your dataset has a city column with 2,000 unique values. How will you encode it?
One-hot would create 2,000 sparse columns, so I would first group rare cities below a frequency threshold into 'Other'. Then options are frequency encoding, out-of-fold target encoding, or mapping cities to useful attributes such as tier, state or population. For boosting models like CatBoost or LightGBM, native categorical handling also works well. I would compare options with cross-validation.
30
Labels for your loan model arrive only after 6 months. How do you monitor it meanwhile?
I would rely on proxy signals: input data drift with PSI, prediction score distribution, approval rates by segment, and early indicators like first missed payment at 30 or 60 days. Once enough early outcomes arrive, I would check performance on these. I would also set up a delayed evaluation job that computes full metrics as labels mature and compares them with the validation baseline.
Tips to crack the American Express Machine Learning interview
Learn credit card business basics like spend, revolve, delinquency and customer lifetime value for analytics interviews.
Practise SQL, Python and statistics, including model evaluation for risk or marketing use cases.
Read about American Express's Blue Box values and its strong focus on customer service.
Keep a one-minute story ready for every project on your CV: problem, your part, tools, result.
Practise the hard questions on this page aloud; American Express interviewers usually ask follow-ups on your first answer.
Frequently asked questions
How many rounds are there in the American Express Machine Learning interview?
Candidates usually go through 5 stages: Online assessment (aptitude + coding or analytics); Technical round; Case or domain round; Hiring manager round; HR round. The exact rounds change with the role, team, location and your experience, so confirm the process with the recruiter.
Which topics should I prepare for the American Express Machine Learning interview?
This practice set leans on MLOps and Deployment (6), Decision Trees and Ensembles (5), Data Preprocessing and Feature Engineering (4), Classification Models (4). Revise those first, then practise explaining one or two of your own projects end to end, because most American Express interviewers ask you to walk through real work.
Are these the exact questions asked at American Express?
No. These are curated practice questions that match the skills and difficulty usually tested in banking & finance interviews like American Express's. They are not a leaked or verified list of past questions.
Where does American Express hire Machine Learning professionals in India?
American Express has large teams in Gurugram, Bengaluru. Openings and locations change often, so check the American Express careers page and filter by city and experience.