Intuit Data Science Interview Questions & Answers

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

During training it randomly switches off a fraction of neurons so the network cannot depend on any single unit, acting as a regulariser against overfitting.

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

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.

Use stratified splits, class weights, resampling such as SMOTE, threshold tuning and judge models with precision, recall, F1 or PR-AUC instead of accuracy.

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.

Train fits the model, validation tunes hyperparameters and model choice, and the untouched test set gives a final unbiased estimate of performance.

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.

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).

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.

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.

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

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

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).

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

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

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.

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

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

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 applies Bayes' theorem assuming features are independent given the class. The assumption is rarely true but the model is fast and works well for text.

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.

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

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

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

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.

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

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

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.

Read in chunks or use usecols and dtypes, convert strings to category, avoid apply with row loops in favour of vectorised ops, and consider Polars, Dask or Parquet storage.

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.

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

*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.

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.

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.

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.

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

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

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.

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.

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.

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

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

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

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.

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

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.

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

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

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

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

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.

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

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.

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

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.

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

An epoch is one pass over the training data; a batch is the subset used for one update; an iteration is one weight update on a batch.

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.

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

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.

P(A given B) = P(B given A) x P(A) / P(B). In a medical test it converts test accuracy and disease prevalence into the real chance a positive result means disease.

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

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.

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.

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