Visa Data Science Interview Questions & Answers

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.

*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.

The rule that lets arrays of different shapes operate together by virtually stretching the smaller one, for example adding a scalar or a (3,) vector to a (4,3) matrix.

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

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.

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.

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.

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.

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

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.

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

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

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

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.

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

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

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

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.

The square root of the variance; it measures how far values typically sit from the mean, in the same units as the data.

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.

As the number of independent trials grows, the sample average converges to the true expected value, which is why larger samples give more stable estimates.

A decorator wraps a function to add behaviour such as logging, timing or caching without changing its code. It is applied with the @name syntax above the function.

Splitting text into units such as words, subwords or characters that are mapped to ids; subword methods like BPE handle rare words well.

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.

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.

It lets a model weigh which input positions matter most for each output, computing weighted combinations of values from query-key similarity. It is the core of transformers.

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

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.

A measure of asymmetry. Right-skewed data has a long tail on the right (mean greater than median); left-skewed is the opposite. Log transforms often reduce right skew.

Bias occurs when the sample does not represent the population. Reduce it with random or stratified sampling, higher response rates and by checking sample demographics against the population.

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).

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.

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

Training a meta-model on the predictions of several base models, often using cross-validated predictions to avoid leakage.

Supervised learning trains on labelled data to predict a target; unsupervised learning finds structure such as clusters or components in unlabelled data.

It normalises layer inputs per mini-batch and then rescales them, stabilising and speeding up training and allowing higher learning rates.

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.

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

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

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.

SVM finds the maximum-margin separating hyperplane. Kernels such as RBF compute similarity in a higher-dimensional space implicitly, so non-linear boundaries are possible.

The distribution of sample means approaches a normal distribution as the sample size grows (roughly 30+), whatever the population's shape. It lets us build confidence intervals and run hypothesis tests on means.

It tries candidate splits and picks the one that most reduces impurity — Gini or entropy (information gain) for classification, variance / MSE for regression.

A shallow copy duplicates the outer object but shares nested objects. A deep copy (copy.deepcopy) recursively duplicates everything, so changes to nested items do not leak.

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

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

A method is a function that belongs to an object or class and receives the instance (self) as its first argument.

Measure first with cProfile or timeit, then replace loops with NumPy or Pandas vectorised calls, use built-ins, caching and better data structures.

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

== compares values for equality, while is checks whether two names point to the same object in memory. Use is mainly for None checks.

CNNs use convolutions to find spatial patterns (images). RNNs/LSTMs process sequences step by step but struggle with long context. Transformers use self-attention to look at all tokens at once — parallel and better at long-range context; they power modern LLMs.

RNNs process sequences with a hidden state but struggle with long dependencies. LSTMs add gates that control what to remember or forget, easing the vanishing gradient.

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.

A network that compresses inputs into a small latent code and reconstructs them; used for denoising, dimensionality reduction and anomaly detection.

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.

pd.pivot_table(df, index='region', columns='month', values='sales', aggfunc='sum') reshapes long data into a summary matrix; melt() does the reverse.

Gradients shrink as they pass through many layers (for example with sigmoid), so early layers barely learn. ReLU, residual connections and good initialisation help.

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

Mean is the average, median is the middle value after sorting and mode is the most frequent value. Median is more robust to outliers.

Use filter methods (correlation, chi-square), wrapper methods (RFE), embedded methods (Lasso, tree importance) and domain knowledge, validating each choice with cross-validation.

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

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

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

Use stratified splits, class weights, resampling (SMOTE or undersampling) and threshold tuning, and judge the model with PR-AUC or F1 instead of accuracy.

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.

Monitor input distributions and live metrics, compare to training baselines, and retrain or recalibrate on fresh data when performance drops.

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.

A symmetric bell-shaped distribution defined by mean and standard deviation, where about 68%, 95% and 99.7% of values lie within 1, 2 and 3 standard deviations.

loc selects by label (row and column names, inclusive of the end label); iloc selects by integer position (end-exclusive).

Frequentists treat parameters as fixed and use long-run frequencies; Bayesians treat parameters as distributions updated with data via priors and posteriors, giving direct probability statements.

A range built from sample data that would contain the true parameter in a stated percentage (for example 95%) of repeated samples. It is not the probability that the parameter lies inside this one interval.