Recruiter Call: to check logistics Take Home Data Challenge: about a simple machine learning model building Hiring Manager Call: he went over the role and his vision , what he is looking for etc. Typical Technical Interview: machine learning algorithm questions & your past project questions Final Interview with the Team: met with senior data scientists and the project manager
Preguntas de entrevista [1]
Pregunta 1
What is the bias and variance trade off Go over your past data science project
Me postulé en persona. Acudí a una entrevista en Honeywell (Atlanta, GA) en abr 2025
Entrevista
3 rounds (at least to my knowledge) - > puzzle like assessment, interview with one of the managers, and then technical round assessment
the call with the managers mainly talks about your resume, your projects (know your projects through and through aon what to improve, each ML technique, etc)
Preguntas de entrevista [1]
Pregunta 1
if you were to use a different machine learning technique which could you have used, and asked my questions based on the ml technique being used
Me postulé a través de un reclutador. Acudí a una entrevista en Honeywell (Bengaluru)
Entrevista
The interview process was seamless from start to finish. It included multiple rounds of technical and behavioral interviews. The interviewers were professional and provided clear expectations. Feedback was timely and constructive. Ultimately, the process culminated in a successful job offer.
Preguntas de entrevista [1]
Pregunta 1
Statistical and Probabilistic Reasoning
Explain the difference between correlation and causation.
This question assesses your understanding of fundamental statistical concepts and your ability to apply them in data analysis.
Machine Learning
How do you handle imbalanced datasets?
This question tests your knowledge of common challenges in machine learning and your approach to addressing them.
Data Munging and Exploration
You have a large dataset with missing values. How do you handle them?
This question evaluates your data preprocessing skills and ability to deal with real-world data imperfections.
Model Evaluation
Explain the difference between precision, recall, and F1-score.
This question tests your understanding of key performance metrics and when to use them.
Business Understanding and Problem Solving
How would you approach a problem where you need to predict customer churn?
This question assesses your ability to apply data science to a real-world business problem and develop a solution strategy.
there are 4 interview rounds: 1. Screening round where they ask basic programming questions, ML Algorithms, Deep learning, NLP basic questions. Also some scenario-based questions. The average interview time was 45-60 mins.
Preguntas de entrevista [1]
Pregunta 1
Sorting algorithms, working of ML models like Random Forest. Difference between bagging and boosting. What are activation functions?