Katkat
Back

Decide Whether an LSTM Is Appropriate for Sequence Data

CitadelData Scientist · Technical Screen
EasyData ScientistTechnical ScreenMachine Learning

Last updated

Decide whether an LSTM is appropriate for sequential data by defining the sequence unit, prediction horizon, masking, and time-safe validation. Compare the model with lag-based and simpler baselines while considering data size, overfitting, latency, and maintainability.

You are considering an LSTM for a prediction problem with sequential observations. Explain what an LSTM is designed to capture, how you would prepare and validate the data, and how you would determine whether it is preferable to simpler sequence baselines.

Constraints & Assumptions

  • Sequence lengths may vary and later observations must not leak into earlier predictions.
  • Compute and labeled data are limited enough that model complexity matters.
  • The task could be sequence classification, forecasting, or next-step prediction; clarify which before proposing details.

Clarifying Questions to Ask

  • What is one sequence, what is one time step, and what target is predicted at what horizon?
  • Are observations regularly spaced, and how should missing steps be represented?
  • How much history is available, and which dependencies are expected to matter?
  • Is real-time inference, interpretability, or uncertainty estimation required?

Follow-up questions

  • How can padding affect training, and how would you prevent padded steps from influencing results?
  • What symptoms would suggest the model is overfitting?
  • When might engineered lag features outperform an LSTM?
  • How would you handle a distribution shift in sequence length?