Adobe Data Science Interview Questions & Answers

Retrieval-Augmented Generation fetches relevant documents and gives them to an LLM as context, reducing hallucination and keeping answers grounded in current private data.

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

Predictors that are highly correlated make coefficients unstable. Detect with VIF above about 5-10, then drop or combine features, use PCA or apply regularisation.

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

Accuracy, F1 and confusion matrices for classification, BLEU or ROUGE for generation and summarisation, perplexity for language models, plus human review.

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.

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.

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.

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

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.

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

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.

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.

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

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

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

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.

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.

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

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

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.

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

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.

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.

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

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.

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

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

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

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.

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.

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.

Discriminative models learn P(y given x) directly (logistic regression, SVM). Generative models learn the joint P(x, y) and can generate data (Naive Bayes, GANs).

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.

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.

It computes the gradient of the loss with respect to every weight by applying the chain rule backwards through the network, so gradient descent can update them.

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

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.

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

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.

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

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.

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.

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.

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.

Correlation measures linear association between variables (-1 to 1). A third factor, reverse causality or chance can create it, so causation needs controlled experiments.

This is overfitting. Check for data leakage, simplify the model, add regularization, get more data or augment it, use cross-validation, early stopping and feature selection.

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