Trend Analysis and Anomaly Detection Questions

Covers methods for detecting and interpreting deviations in metric behavior over time and determining whether changes reflect real product or user behavior versus noise. Topics include baseline establishment, seasonality and holiday effects, time series decomposition, smoothing and aggregation choices, statistical detection techniques such as control charts, z scores, EWMA and CUSUM, thresholding strategies, and modern algorithmic approaches like isolation forest or LSTM-based detectors. Also covers visualization and dashboarding practices for communicating trends, setting sensible alerting rules, triage workflows for investigating anomalies, and assessing business impact to prioritize fixes or rollbacks.

MediumTechnical

0 practiced

You observe anomalies across multiple purchase-funnel metrics in several countries. Describe a framework to estimate business impact (e.g., revenue or DAU loss) to prioritize which anomalies to investigate first. List what additional data you'd request and how you'd present a prioritized list to stakeholders.

EasyTechnical

0 practiced

List the key visualization and dashboard features a data engineer should provide to help product teams triage anomalies. Include recommended chart types, drilldown capabilities, annotations (deploys/feature flags), contextual metadata in alerts, and an example layout for a dashboard panel that supports triage.

MediumTechnical

0 practiced

Describe methods to detect feature drift and label drift for anomaly detection models in production. Include specific metrics you would compute (e.g., PSI, KL divergence), sampling frequency, and automated actions to take when drift exceeds thresholds.

HardTechnical

0 practiced

Implement a Poisson CUSUM detector for daily count data in Python. Provide a function detect_poisson_cusum(counts: List[int], baseline_rate: float, k: float, h: float) -> List[int] that returns the indices where the alarm triggers, and explain how to choose baseline_rate, k (reference value), and h (threshold) in practice.

HardTechnical

0 practiced

You observe a recurring weekly false-positive spike in anomaly alerts that correlates with ad-bidding system updates deployed each Tuesday. Create an investigative plan that identifies hypotheses, data to collect (logs, request traces, feature flags), experiments to validate hypotheses, and changes to detection and instrumentation to eliminate the false positives.

Unlock Full Question Bank

Get access to hundreds of Trend Analysis and Anomaly Detection interview questions and detailed answers.

Join thousands of developers preparing for their dream job.