How would you model stock price prediction?

Q: How would you model stock price prediction?

This question evaluates competency in applying machine learning to financial time-series, covering target definition, data selection, feature engineering, model choice, validation, evaluation metrics, and production considerations.

Q: How do I approach Machine Learning interview questions?

Machine Learning questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master machine learning interviews.

Q: What difficulty level is this interview question?

This is a medium difficulty Machine Learning question, commonly asked during Technical Screen rounds at Millennium.

Q: What role is this question designed for?

This question is commonly asked for Software Engineer candidates at Millennium during technical interviews.

Question

Loading...

Scenario

You are asked to use machine learning to predict stock prices (or more realistically, predict future returns / price direction) for a trading use case.

Questions

Target definition: What exactly would you predict (e.g., next-day close, next-hour return, direction, volatility)? Why?
Data: What data sources would you use (market data, fundamentals, news, alternative data)? What is the minimum viable dataset?
Features: What features would you engineer from the data?
Modeling: What model families would you consider and why (linear models, tree-based, deep learning, time-series models)?
Training & validation: How would you split data over time to avoid leakage? How would you tune hyperparameters?
Evaluation: What metrics would you use (ML metrics and trading metrics)?
Pitfalls: How would you address non-stationarity, regime changes, data snooping, survivorship bias, and transaction costs?
Production considerations: How would you deploy, monitor, and retrain the model?

How would you model stock price prediction?

Quick Overview

Scenario

Questions

Solution

Comments (0)