Uber Data Science Interview Questions & Answers

Add a classification head, freeze or gradually unfreeze layers, use a small learning rate, train on labelled data with validation, and track F1 per class.

Raising the threshold improves precision but lowers recall. Fraud detection leans to recall, while spam filters often prefer precision; choose by the cost of each error.

Regression predicts continuous values such as price; classification predicts discrete categories such as spam or not spam.

The probability of seeing a result at least as extreme as the observed one if the null hypothesis were true. A small p-value is evidence against the null, not proof that the alternative is true.

Parametric tests assume a distribution (usually normal) and use means; non-parametric tests such as Mann-Whitney use ranks and make fewer assumptions.

Precision = TP / (TP + FP). Recall = TP / (TP + FN). Prefer recall when missing a positive is costly — for example disease screening or fraud detection.

Type I = false positive (rejecting a true null), probability α. Type II = false negative (missing a real effect), probability β. Power = 1 − β.

Bagging trains models in parallel on bootstrap samples and averages them (reduces variance, e.g. Random Forest). Boosting trains models one after another, each fixing the previous errors (reduces bias, e.g. XGBoost).

Calibration checks whether predicted probabilities match real frequencies (e.g. 70% predictions are right about 70% of the time). Fix with Platt scaling or isotonic regression.

It checks whether observed category counts differ from expected counts, used for independence between two categorical variables and for goodness of fit.

*args collects extra positional arguments into a tuple; **kwargs collects extra keyword arguments into a dict. They make function signatures flexible and are common in wrappers and decorators.

It combines gradient boosting with regularisation, handling of missing values, parallel tree construction and speed optimisations, and it performs strongly on tabular data.

Both measure node impurity; Gini is cheaper to compute and entropy is slightly more sensitive to class balance, with similar trees in practice.

Tie metrics to business outcomes such as cost saved, show feature importance or SHAP values, give example predictions and be transparent about limitations.

Information from outside the training window, such as future data or test statistics, enters training and inflates performance. Split first, then fit scalers and encoders on training data only.

Use grid search, random search or Bayesian optimisation with cross-validation, starting with a coarse random search and narrowing the promising ranges.

Package the model behind an API with versioning, track latency and errors, monitor input drift and prediction quality, and automate retraining with rollback.

It predicts from the k nearest labelled points. It is simple but slow at prediction time, sensitive to scaling and irrelevant features, and weak in high dimensions.

Convolution filters slide over the input to detect local patterns, pooling reduces size, and deeper layers combine edges into shapes and objects. Used mainly for images.

Activations add non-linearity so networks can learn complex patterns. ReLU (max(0, x)) is cheap and reduces vanishing gradients compared with sigmoid/tanh; Leaky ReLU avoids 'dead' neurons.

The ROC curve plots true positive rate against false positive rate across thresholds. AUC is the probability that a random positive is ranked above a random negative; 0.5 is chance.

Use the IQR rule (below Q1-1.5 IQR or above Q3+1.5 IQR), z-scores beyond 3, box plots or model-based methods such as Isolation Forest, then decide whether to cap, remove or keep them.

A function using yield that produces values lazily, one at a time. It saves memory when processing large files or streams because the full sequence is never held in RAM.

Layers of connected neurons that apply weights, biases and activation functions to learn complex patterns, trained by backpropagation.

Bias is error from overly simple assumptions (underfitting). Variance is sensitivity to the training data (overfitting). More model complexity lowers bias but raises variance — aim for the lowest total error using cross-validation and regularization.

A table of true positives, false positives, true negatives and false negatives from which accuracy, precision, recall and F1 are calculated.

The probability of seeing a result at least this extreme if the null hypothesis were true. A small p-value (for example < 0.05) is evidence against the null hypothesis.

Modelling the count of events in a fixed interval when events occur independently at a constant average rate, such as calls per hour or defects per batch.

Small anonymous one-line functions, handy as arguments to sort, map, filter or Pandas apply.

A set stores unique values with no keys; a dictionary stores key-value pairs with unique keys. Both use hashing, so lookups are O(1) on average.

They store same-type values in contiguous memory and run vectorised operations in compiled C, avoiding Python loop overhead and per-object type checks.

The model memorises noise and fails on new data. Prevent it with more data, simpler models, regularisation, cross-validation, early stopping and dropout.

int, float, complex, bool, str, list, tuple, set, dict and NoneType. Mutable ones are list, set and dict; the others are immutable.

First understand why data is missing. Then drop rows or columns with too many nulls, impute with mean/median/mode or a model (KNN), add a 'was_missing' flag, and fit imputers on training data only.

Split the data into k folds, train on k−1 folds and validate on the remaining one, rotate and average the scores. It gives a more reliable estimate than one split and helps tune hyperparameters without touching the test set.

It projects data onto orthogonal directions of maximum variance to reduce dimensions, remove correlation and speed up models, at some cost of interpretability.

map works element-wise on a Series, apply works on a Series or along a DataFrame axis, and applymap (now DataFrame.map) applies a function to every cell.

Putting features on comparable ranges using standardisation or min-max scaling. Distance-based and gradient-based models (KNN, SVM, regression, neural nets) need it; tree models do not.

Pearson measures linear relationships on continuous data; Spearman uses ranks, so it captures monotonic relationships and is less sensitive to outliers.

ReLU for hidden layers, sigmoid for binary outputs, softmax for multi-class outputs and tanh when zero-centred outputs help; Leaky ReLU avoids dead neurons.

Reusing a model pretrained on a large dataset and fine-tuning it on a smaller task-specific dataset, saving data, time and compute.

df.drop_duplicates(subset=[...], keep='first') removes repeated rows; use duplicated() first to inspect what will be dropped.

Start with a sensible default such as 1e-3 for Adam, run a learning-rate range test, and use schedulers or warm-up while watching the loss curve.

It assigns points to the nearest centroid and updates centroids until stable. Choose k with the elbow method, silhouette score or business context.

A mutex in CPython that lets only one thread execute Python bytecode at a time. Use multiprocessing for CPU-bound work and threads or asyncio for I/O-bound work.

A forest averages many trees trained on bootstrapped rows and random feature subsets, which cuts variance and overfitting at the cost of interpretability.

Transformers use self-attention to process all tokens in parallel and capture long-range context, making them faster to train and more scalable than sequential RNNs.

Term Frequency × Inverse Document Frequency: a word scores high if it is frequent in one document but rare across all documents. A classic way to turn text into numeric features.

It fits a line minimising squared error. Assumes linearity, independent errors, constant variance (homoscedasticity), normally distributed residuals and no strong multicollinearity.

They build a list in one readable expression, for example [x*x for x in data if x > 0]. They are usually faster than an equivalent for-loop with append.

Regularization adds a penalty on weights to reduce overfitting. L1 (Lasso) adds |w| and can push features to exactly zero. L2 (Ridge) adds w² and shrinks weights smoothly.

Define the hypothesis and one primary metric, calculate sample size from the baseline, minimum detectable effect, α and power, randomise users, run for full business cycles, check for sample-ratio mismatch, then test both statistical and practical significance.

Use target or frequency encoding with cross-validation, hashing, embeddings or grouping rare categories, instead of huge one-hot matrices.

Define churn and the prediction window, build behavioural features, split by time, train and compare models, evaluate with recall and lift, explain drivers and monitor drift after deployment.

Define churn and the prediction window → build usage and billing features → handle imbalance → train gradient boosting → evaluate with PR-AUC and lift → explain with SHAP → deploy as batch scoring or an API → monitor drift → hand top-risk users to the retention team.

An iterable can produce an iterator (it has __iter__); an iterator has __next__ and remembers its position. A for-loop calls iter() on the iterable and then next() repeatedly.

An optimisation method that updates weights in the opposite direction of the loss gradient. The learning rate sets the step size: too high and it diverges, too low and it is slow. Variants include SGD, mini-batch and Adam.

Power is the probability of detecting a real effect. Increase it with a larger sample, a bigger effect size, lower noise or a higher significance level.