Katkat

practice a little every day, paws crossed ♡

Quantitative Researcher Interview Questions

Practice 9403 coding, system design and machine learning questions from 546 companies, sorted by role, topic and interview round. Every question has step-by-step hints, a code runner that supports 8 languages and an AI mentor; members also get the full solution walkthrough.

9403
Questions
546
Companies
11
Topics
8
Languages

Showing 31–59 of 59 results

  • Point72MediumQuantitative Researcher
    Encode Categorical Variables Across Model Families

    Choose categorical encodings for linear, tree, and neural models while handling intercept rank, unseen values, and high cardinality.

    Machine LearningOnline Assessment
  • Point72MediumQuantitative Researcher
    Estimate Factor Returns and Residual Returns

    Derive weighted factor-return estimates from a sample, then compute residual returns across a larger trading universe with stable linear algebra.

    Statistics & MathOnline Assessment
  • Point72MediumQuantitative Researcher
    Explain Ensemble Learning and Its Main Families

    Explain why combining multiple models can improve predictions. Cover data and labels, leakage-safe features, baselines and model choice, offline evaluation, deployment constraints, monitoring, and drift.

    Machine LearningTechnical Screen
  • Point72MediumQuantitative Researcher
    Explain Transformer Encoder and Decoder Behavior

    This question evaluates knowledge of Transformer architecture and generative language modeling, specifically the encoder versus decoder roles, attention patterns and causal masking, plus mechanisms behind stochastic text generation such as sampling and temperature.

    Machine LearningTechnical Screen
  • Point72MediumQuantitative Researcher
    Find the Minimum in a Rotated Sorted Array

    A strictly increasing array of distinct integers has been rotated at an unknown pivot. Work through the function contract, boundary cases, correctness argument, and time and space complexity expected in a production-quality solution.

    Coding & AlgorithmsTechnical Screen
  • Point72HardQuantitative Researcher
    Find the Two Heaviest Balls with Minimum Comparisons

    There are 32 balls with distinct weights. Explain the assumptions and derivation clearly, check edge cases, and show how the result changes when those assumptions no longer hold.

    Statistics & MathTechnical Screen
  • Point72MediumQuantitative Researcher
    Formulate a Single-Period Stat-Arb Objective

    Formulate a convex single-period statistical-arbitrage objective balancing expected return against covariance risk, with consistent units.

    Statistics & MathOnline Assessment
  • Point72MediumQuantitative Researcher
    Linearize an L1 Trading Penalty

    Linearize weighted absolute trading costs with auxiliary variables, complete LP constraints, the correct objective sign, and an equivalence proof.

    Statistics & MathOnline Assessment
  • Point72MediumQuantitative Researcher
    Model Trading Frictions in Portfolio Optimization

    Extend a stat-arb objective with unit-consistent commissions, spread, slippage, market impact, turnover, borrow, and concentration costs.

    Statistics & MathOnline Assessment
  • Point72MediumQuantitative Researcher
    Prove That Lasso Can Be Written as a Quadratic Program

    Derive the Lasso quadratic-program formulation and prove equivalence, convexity, minimizer correspondence, and rank-related uniqueness.

    Statistics & MathTechnical Screen
  • Point72MediumQuantitative Researcher
    Solve Three Probability Models

    Solve three independent probability questions. Explain the assumptions and derivation clearly, check edge cases, and show how the result changes when those assumptions no longer hold.

    Statistics & MathTechnical Screen
  • SquarepointMediumQuantitative Researcher
    Choose Between an Array and a Linked List

    Tests understanding of arrays versus linked lists beyond asymptotic Big O notation, focusing on CPU cache locality, memory layout overhead, reference stability, and practical queue design.

    Software Engineering FundamentalsTechnical Screendata-structurescache-localitymemory-hierarchy
  • SquarepointMediumQuantitative Researcher
    Count Files Safely from Bash

    Tests command-line proficiency and Bash scripting fundamentals by requiring a robust mechanism to count regular files across a directory tree while handling tricky filenames, symlinks, and recursion correctly.

    Software Engineering FundamentalsTechnical Screenbashlinuxshell-scripting
  • SquarepointMediumQuantitative Researcher
    Find Values Whose Removal Minimizes Pairing Cost

    Determine all unique values from an odd-length array whose removal leaves an even-length array that can be partitioned into pairs with minimum total absolute difference.

    Coding & AlgorithmsTechnical Screenarrayssortingprefix-sum
  • SquarepointMediumQuantitative Researcher
    Shortest Subarray with at Least K Distinct Values

    Determine the minimum length of a contiguous subarray that contains at least k distinct elements. This problem tests sliding-window techniques, hash map management, and linear-time optimization.

    Coding & AlgorithmsTechnical Screensliding-windowhash-tabletwo-pointers
  • Two SigmaMediumQuantitative Researcher
    Daily Temperatures by Town: Linear Models to Predict NYC Temperature

    This question evaluates proficiency in ordinary least squares linear regression (with intercept), basic statistical summaries such as standard deviation and median, and model-evaluation metrics like in-sample mean squared error applied to aligned daily time-series temperature data.

    Machine LearningTechnical Screen
  • Two SigmaMediumQuantitative Researcher
    Linear Interpolator with Extrapolation

    This question evaluates understanding of piecewise linear interpolation and extrapolation, numerical robustness with floating-point values, and algorithmic competencies such as sorting and efficient query location for large datasets.

    Coding & AlgorithmsTechnical Screen
  • Virtu FinancialHardQuantitative Researcher
    Approximate a Binomial Upper Tail with a Normal Distribution

    This question tests the application of the Normal approximation to the Binomial distribution, the use of continuity correction, and the ability to evaluate the error bounds of this approximation.

    Statistics & MathOnsiteStatisticsProbabilityNormal Approximation
  • Virtu FinancialHardQuantitative Researcher
    Approximate a Rare-Event Binomial Probability

    This problem tests the application of the Poisson approximation to binomial distributions for rare events and the evaluation of the error bounds associated with this approximation.

    Statistics & MathOnsiteProbabilityPoisson DistributionBinomial Distribution
  • Virtu FinancialHardQuantitative Researcher
    Birthday Collisions and the Closest Pair of Birthdays

    This problem tests your understanding of probability theory, specifically the generalized birthday paradox, and your ability to analyze spacing distributions of random variables.

    Statistics & MathOnsiteProbabilityStatisticsCombinatorics
  • Virtu FinancialHardQuantitative Researcher
    Compare Two Strategies for Getting Ten Consecutive Heads

    This problem tests your ability to model probability through recursion and expectation, specifically comparing the efficiency of two distinct strategies for achieving a target streak of coin tosses.

    Statistics & MathOnsiteProbabilityExpectationRecurrence
  • Virtu FinancialHardQuantitative Researcher
    Maximum Edges in a Triangle-Free Graph

    Determine the maximum number of edges an undirected, simple graph on n vertices can have without containing any triangle (K3), and construct one such extremal graph.

    Coding & AlgorithmsOnsitegraph-theorymathcombinatorics
  • Virtu FinancialHardQuantitative Researcher
    Maximum Total Height of Mountain-Shaped Towers Under Per-Plot Height Caps

    Each plot in a row has a maximum allowed tower height. Choose tower heights that rise to a single peak and then fall, never exceeding any cap, so that the total height is as large as possible. Tests reasoning about the peak position, per-position caps, and 64-bit sums.

    Coding & AlgorithmsOnline Assessment
  • Virtu FinancialHardQuantitative Researcher
    Minimum Number of Transfers to Settle All Debts in a Group

    Given a list of past loans between people, compute the minimum number of new money transfers needed so that everyone's net balance returns to zero. Tests reducing a transaction log to net balances and searching for the fewest settling transfers under small input bounds.

    Coding & AlgorithmsOnline Assessment
  • Virtu FinancialHardQuantitative Researcher
    Reach a Target Pair by Repeatedly Adding One Coordinate to the Other

    Starting from a pair of positive integers, each move adds one coordinate to the other. Decide whether an exact target pair can be reached. Tests reasoning about reachability when values go up to one billion and simulating every forward move is far too slow.

    Coding & AlgorithmsOnline Assessment
  • VoleonMediumQuantitative Researcher
    Bound R-Squared for Individual and Combined OLS Regressions

    Derive in-sample OLS R-squared bounds and the joint-model range from individual scores, including intercept assumptions, predictor correlation, and out-of-sample exceptions.

    Statistics & MathTechnical Screen
  • VoleonMediumQuantitative Researcher
    Explain a Sorting Algorithm Such as Merge Sort: Mechanics, Correctness, Complexity

    Explain a sorting algorithm of your choice, such as merge sort, in a technical screen for a quantitative role. Tests whether you can describe the split and merge steps, trace a small example, argue correctness, derive time and space complexity, and discuss stability and alternatives.

    Software Engineering FundamentalsTechnical Screen
  • VoleonMediumQuantitative Researcher
    Reason About Train and Test Loss Under Regularization and More Data

    Reason about train/test gaps, high losses, regularization strength, and learning curves while separating statistical tendencies from finite-sample guarantees.

    Machine LearningTechnical Screen
  • VoleonMediumQuantitative Researcher
    Return Words in Repeated Anagram Groups

    Return all input occurrences belonging to repeated anagram groups, preserving order and duplicates with multiplicity-aware letter-count signatures.

    Coding & AlgorithmsTechnical Screen