Time Series Interview Questions
Time-series is where quant theory meets the messy reality that data points arrive in order and depend on their own past. This playlist builds you from the foundations -- stationarity, autocorrelation, and the AR/MA/ARMA toolkit -- up through the two engines that drive most desks: volatility modeling
How to think about time series questions
Time-series problems break the one assumption the rest of statistics leans on: the observations aren't independent — today depends on yesterday. The whole subject is machinery for taming that dependence so you can forecast and test honestly.
STATIONARITY FIRST
Before you can model anything you need the statistical properties to hold still over time — constant mean, constant variance, autocorrelation that depends only on the lag. Differencing or de-trending to reach stationarity is the first move; a unit root is the warning that you haven't yet.
AR, MA, AND THE MEMORY
Two atoms build most models: the present is a weighted echo of past values (AR) or past shocks (MA). Reading the autocorrelation and partial-autocorrelation patterns tells you which, and how far back the memory reaches — the same correlation bookkeeping as regression, indexed by time.
The thread: make it stationary, then ask how the past leaks into the present — through old values, old shocks, or both.
Time Series questions (47)
- Maximum Drawdown of a Price Series
- GARCH(1,1) Conditional and Unconditional Variance
- Stationarity Testing and Residual Autocorrelation Diagnostics
- Recovering AR(2) Coefficients From Autocorrelations
- GARCH Model for Volatility
- Identifying and Fitting an MA(q) Model from ACF and PACF Patterns
- GARCH vs HAR-RV for Volatility Forecasting
- Detrending and Moving Average Features for Forecasting
- Random Walk: Moments, Differencing, and Spurious Regression
- ARMA Process Stationarity, Invertibility, and Diagnostic Workflow
- ARMA(1,1) Stationarity, Forecasting, and Estimation
- Detecting the Direction of Time in a Price Series
- AR(1) Mean Reversion: OLS Estimation, Hypothesis Testing, and Trading Rule
- RiskMetrics EWMA Variance Forecasting and Half-Life
- Engle-Granger Cointegration Trading Signal
- Spurious Regression and Cointegration
- Predictive Content of Order Imbalance
- Time-Series Cross-Validation Without Lookahead Bias
- Block Bootstrap for Trading Signal Robustness
- Yule-Walker Equations, PACF, and AR Order Selection
- VaR and Expected Shortfall under GARCH(1,1)
- Cointegration: Engle-Granger Procedure and Error Correction
- Engle's ARCH LM Test
- Realized Kernel Estimator Under Microstructure Noise
- Hidden Markov AR(1) via EM
- Unit Root Testing With a Structural Break
- ACF and PACF of an ARMA(1,1) Process
- Kalman Filter: Prediction, Update, and Steady-State Gain
- Time-Varying Beta via Kalman Filter
- Comparing Volatility Forecasting Models: GARCH, Realized Vol, and HAR-RV
- Estimating the Hurst Exponent via Rescaled Range Analysis
- Johansen Cointegration Test and Walk-Forward Spread Validation
- Detecting Multiple Structural Breaks via Dynamic Programming
- Simpson's Paradox in Time Series Correlation
- AR(1) Forecasting Error Variance and MLE
- Maximum Drawdown in a Sliding Window
- GARCH(1,1) Stationarity, Unconditional Variance, and Shock Propagation
- Diebold-Mariano Forecast Comparison Test
- Effective Sample Size Under Autocorrelation
- GARCH Quasi-Maximum Likelihood with Student-t Innovations
- GPH Log-Periodogram Estimator for Long Memory
- Autoregressive Conditional Duration Model
- Rolling Heteroskedastic t-Statistic Under GARCH
- Two-State Volatility HMM and the Hamilton Filter
- GMM Estimation of AR(1) Under Heteroskedasticity
- Stochastic Volatility and Particle Filtering
- Kalman Filter for a Latent Mean-Reverting Signal
Time Series interview questions FAQ
What kind of time series questions show up in quant interviews?
This page collects 47 time series problems that recur in quant trading and research interviews, each with a full worked solution and the intuition behind it. They range from quick warmups to the harder variants firms use to separate candidates.
How hard are time series interview questions?
The set spans 3 easy, 12 medium and 32 hard problems. Most sit at medium difficulty — a few minutes of clean reasoning — with a harder tail that rewards knowing the canonical approach rather than grinding.
How should I practice time series for quant interviews?
Work through them by difficulty, starting just below your level, and write the solution out before checking. 5 are free to open with the full worked solution, so you can judge the quality first. Focus on the recurring patterns rather than memorizing answers — the same handful of ideas generate most variants.
Are these real quant interview questions?
They are a curated set drawn from our problem bank — the kind of time series question that actually appears in quant interviews, rewritten for clarity with solutions we author ourselves. We don't claim any single wording is verbatim, and every problem carries a full solution.