Swiggy Data Scientist Interview Questions
& Process
Real candidates share what happened, how many rounds they had,
and how the experience turned out.
Based on 22 interview experiences · FREE TO READ
Candidate interview experiences
First-hand accounts from people who interviewed at Swiggy.
Swiggy
Data Scientist
Mid Average Positive experience No offer 3 rounds
Interview process
Technical screen Technical screen Technical screen
Interview formats
Coding Technical Technical
it was smooth there was three round first was python , second was sql , third was ml round interviewer was nice and helpfull and will help u to think on the problem they asked so we will need to add the game
Confirmed questions1 question
- Tell me about regularization, classical ML, and distillation.
Swiggy
Data Scientist
Entry Average Neutral experience No offer 3 rounds
Interview process
Technical screen Technical screen Recruiter call
Interview formats
Coding Technical
The first round was about DSA and SQL, featuring two easy LeetCode questions and three SQL questions like rank, having, and group by. The second round focused on ML, where classifiers were discussed. Finally, the third round was an HR interview.
Confirmed questions4 questions
- Can you sort the array?
- How would you print the 2nd largest number in an array?
- Solve two easy LeetCode questions related to data structures and algorithms.
Swiggy
Data Scientist Intern
Intern Average Neutral experience No offer 2 rounds
Interview process
Recruiter call Technical screen Technical screen
Interview formats
Technical Coding Technical
The interview had 2 rounds. Round 1 was a technical discussion focused on resume projects. It started with introductions, then moved to discussing a favorite project. Questions covered data sourcing, preprocessing, statistical concepts like correlation and heatmaps, handling class imbalance, ideal data size, and model-specific details like overfitting and OOB scores. Log transformation was also discussed. The conversation then shifted to an NLP project, covering its problem statement, motivation, TFIDF, Bag of Words, and comparing model choices like Random Forest and Logistic Regression. Metrics like Precision and Recall, and the loss function for Logistic Regression were also covered. Round 2 involved ML coding using Python (Numpy, Pandas) and SQL, with no DSA questions. A k-means clustering problem and an SQL query for the 5th highest salary were presented.
Confirmed questions8 questions
- Did you want to talk about a favorite project, or should I pick one from your resume?
- Which project are you referring to, and where did you source the data?
- Can you tell me about the data preprocessing steps you took?
Swiggy Data Scientist Interview Questions
Quoted word for word from Swiggy interview reports.
“Given that in any 15-minute timeframe, there's a 20% chance of observing at least one shooting star, what is the likelihood of seeing at least one shooting star within an hour?”
Read reports →“Between a Decision Tree and a Random Forest, which is more likely to overfit, and why?”
Read reports →“Can you explain the formula for TFIDF Vectorizer, and what do the letters stand for?”
Read reports →“How would you print the 2nd largest number in an array?”
Read reports →“In this particular scenario, why did the DecisionTreeClassifier achieve better accuracy than the RandomForest?”
Read report →“Are there other metrics to evaluate accuracy apart from the standard Accuracy score?”
Read report →“What is considered a good amount of data for a machine learning model?”
Read report →“What method would you use to determine the number of clusters in a clustering algorithm?”
Read report →“In a table containing Employee_name and Salary, how would you find the employee with the 5th highest salary?”
Read report →Formats, difficulty and experience
Across all 22 Swiggy interview reports.