Dunnhumby Lead Applied Data Scientist Interview Questions and Answers

Sql and basis python

Business related case study

Q1. Previous Project discussion
Add your answer

The coding round was relatively easy. A sufficient amount of preparation on LeetCode should be beneficial, along with reviewing the sample questions.

Q1. All theoretical questions about Linear Regression
Add your answer
Q2. Past projects
Add your answer

2 sections. First, multiple choice questions regarding Ml algo, SQl. Second, ML coding problem.

Q1. Details about dimensionality reductions, the difference between bagging and boosting techniques, details about XgBoost, and metrics to choose for the given Ml classification problem.
Add your answer

Q1. Interview with HR manager, behavioural questions.
Add your answer

Q1. Interview with business leadership.
Add your answer

Q1. Initially asked to introduce myself and my work experience.
Add your answer
Q2. Based on my work experience, the panel asked further questions around my projects, going deeper into the basics of machine learning algorithms that I used for regression models and time series forecasting ...read more
Add your answer

Q1. The second round was more of like techno-managerial round where the panel asked me how I did my latest project, what were the obstacles faced, how did I overcome them, etc.
Add your answer

Q1. The final round was with the HR where the salary negotiation part happened.
Add your answer

Basic coding questions related to data science

Q1. How to handle imbalanced data in text analytics?
Ans. 
Imbalanced data in text analytics can be handled by techniques like oversampling, undersampling, and SMOTE.
• Use oversampling to increase the number of instances in the minority class

• Use undersampling to decrease the number of instances in the majority class

• Use SMOTE to generate synthetic samples for the minority class

• Use cost-sensitive learning algorithms to assign higher misclassification costs to the minority class

• Use...read more
Answered by AI
Add your answer

Q1. Business case study related to Data science
Add your answer

The test consisted 1 programming question, 2 SQL questions, 2 Python questions, and 10 ML questions. The difficulty level was from easy to medium range. However, the platform was very slow and it was a timed test. They should either conduct the test in a friendly platform or increase the time allotted for each section.

Q1. Difference between Ridge and Lasso regression
Ans. 
Ridge and Lasso regression are both regularization techniques used in linear regression to prevent overfitting.
• Ridge regression adds a penalty equivalent to the square of the magnitude of coefficients, while Lasso regression adds a penalty equivalent to the absolute value of the magnitude of coefficients.

• Ridge regression shrinks the coefficients towards zero but never exactly to zero, while Lasso regression can shrink ...read more
Answered by AI
Add your answer

Q1. Difference between boosting and bagging
Ans. 
Boosting focuses on improving the performance of weak learners sequentially, while bagging uses parallel ensemble learning with bootstrapping.
• Boosting combines multiple weak learners to create a strong learner by giving more weight to misclassified instances in each iteration.

• Bagging creates multiple subsets of the training data through bootstrapping and trains each subset independently to reduce variance.

• Examples: Ada...read more
Answered by AI
Add your answer

Python Coding Questions with

Bubble sort example Question using python

Previous projects based questions