Data Science & ML

Time Series & Forecasting

Time analysis, stationarity, ARIMA, Prophet, seasonal decomposition, forecasting metrics, backtesting

22 interview questionsยท
Mid-Level
1

What is a time series?

Answer

A time series is a sequence of data points indexed in chronological order. Observations are collected at regular intervals (hourly, daily, monthly) and often exhibit temporal dependencies. Classic examples include stock prices, temperatures, and monthly sales.

2

What are the three main components of a time series in classical decomposition?

Answer

Classical time series decomposition identifies three components: trend (long-term evolution), seasonality (repetitive patterns at fixed intervals), and residual (unexplained random noise). This decomposition can be additive or multiplicative depending on the nature of the data.

3

What is stationarity in a time series?

Answer

A time series is stationary when its statistical properties (mean, variance, autocorrelation) remain constant over time. Stationarity is a fundamental assumption for many forecasting models like ARIMA. A non-stationary series often needs to be transformed (differencing) before modeling.

4

Which statistical test is commonly used to check the stationarity of a time series?

5

How to make a non-stationary time series stationary?

+19 interview questions

Master Data Science & ML for your next interview

Access all questions, flashcards, technical tests, code review exercises and interview simulators.

Start for free