TVS Motor Senior Data Scientist Interview Questions and Answers

45 mins 15 min mcq data science and 30 mins 1 dsa problem

Q1. Python - All subsets of a list.
Ans. 
Generate all possible subsets of a given list in Python.
• Use itertools.combinations to generate all possible combinations of the list elements.

• Convert the combinations to lists and store them in a new list to get all subsets.
Answered by AI
Add your answer
Q2. Sql query - Customers who have ordered all products from all categories.
Ans. 
Use a SQL query to find customers who have ordered all products from all categories.
• Join the Customers, Orders, and Products tables

• Group by customer and count the distinct products ordered

• Filter for customers who have ordered the total number of products available in each category
Answered by AI
Add your answer
Q3. Importance of feature engineering.
Ans. 
Feature engineering is crucial in data science as it involves selecting, transforming, and creating new features to improve model performance.
• Feature engineering helps in improving model accuracy by providing relevant and meaningful input variables.

• It involves techniques like one-hot encoding, scaling, normalization, and creating interaction terms.

• Feature engineering can help in reducing overfitting and improving model...read more
Answered by AI
Add your answer
Q4. Questions on project.
Add your answer
Q5. What is GAN.Have you worked with it.
Ans. 
GAN stands for Generative Adversarial Network, a type of neural network used for generating new data.
• Consists of two neural networks - generator and discriminator

• Generator creates new data samples while discriminator tries to distinguish between real and generated data

• Used in image generation, text generation, and other creative applications
Answered by AI
Add your answer

Q1. Discussion on project.Demo of project.
Add your answer
Q2. Analysis sql query - whether class 11 marks or class 12 marks is greater., table given which contains student name,class,11th marks,12th marks.
Add your answer
Q3. Similar table. Find students who scored more than avg marks of both 11th and 12th.
Ans. 
Find students who scored more than avg marks in both 11th and 12th grades.
• Calculate the average marks for each student in 11th and 12th grades.

• Compare each student's marks with the respective average marks to find those who scored higher in both grades.
Answered by AI
Add your answer
Q4. What is Cost function.
Ans. 
Cost function is a mathematical function that measures the error between predicted values and actual values in a machine learning model.
• Cost function helps in optimizing the parameters of a model to minimize the error.

• Common cost functions include Mean Squared Error (MSE) and Cross Entropy Loss.

• It is used in training machine learning models through techniques like gradient descent.

• The goal is to find the parameters tha
Answered by AI
Add your answer
Q5. What is entropy.
Ans. 
Entropy is a measure of disorder or randomness in a system.
• Entropy is used in information theory to quantify the amount of uncertainty involved in predicting the value of a random variable.

• It is often used in machine learning to measure the impurity or disorder in a dataset.

• In thermodynamics, entropy is a measure of the amount of energy in a physical system that is not available to do work.
Answered by AI
Add your answer
Q6. What is ginni coefficient.
Ans. 
Gini coefficient is a measure of statistical dispersion intended to represent the income or wealth distribution of a nation's residents.
• Gini coefficient ranges from 0 to 1, where 0 represents perfect equality and 1 represents perfect inequality.

• A Gini coefficient of 0.4 is considered moderate inequality, while 0.6 or higher is considered high inequality.

• It is commonly used in economics to measure income inequality with...read more
Answered by AI
Add your answer
Q7. What will happen if linear regression is used for classification
Ans. 
Using linear regression for classification can lead to inaccurate predictions and unreliable results.
• Linear regression assumes a continuous output, making it unsuitable for discrete classification tasks.

• It may not handle outliers well, leading to incorrect classification boundaries.

• The predicted values may fall outside the 0-1 range for binary classification.

• Logistic regression is a more appropriate choice for classifi
Answered by AI
Add your answer

Q1. Pair sum problem in python.Discussion on space time complexity.
Add your answer
Q2. Discussion on project.What algorithms used and why.
Add your answer

Q1. Introduction your self
Add your answer
Q2. What are the language you learned
Ans. 
I have learned multiple programming languages including Python, R, SQL, and Java.
• Python

• R

• SQL

• Java
Answered by AI
Add your answer

It was campus placement. We were givien the topic "future of AI and ML in automobile industry". The time given was around 15mins. The explained the process in great detail and very clearly.

Q1. CV and basic of ML
Add your answer
Q2. What if questions. For eg, if you want to launch a new EV in market then what will be your approach What if you are the CEO.. ETC
Add your answer

Q1. Ethical questions
Add your answer
Q2. Besic HR questions like why this company
Add your answer

Q1. Tell me about yourself
Add your answer
Q2. Questions from projects which was mentioned on resume
Add your answer

Q1. Fitment based questions
Add your answer
Q2. Explain a project
Ans. 
Developed a machine learning model to predict customer churn for a telecom company.
• Collected and cleaned customer data including usage patterns and demographics

• Used classification algorithms like Random Forest and Logistic Regression to build the model

• Evaluated model performance using metrics like accuracy, precision, and recall
Answered by AI
Add your answer

Math, English, reasoning

Q1. Asked me about expected salary
Add your answer

Q1. What is difference between lstm and rnn
Ans. 
LSTM is a type of RNN that addresses the vanishing gradient problem by using memory cells.
• RNN stands for Recurrent Neural Network, a type of neural network that processes sequential data.

• LSTM stands for Long Short-Term Memory, a type of RNN that includes memory cells to retain information over long sequences.

• LSTM is designed to overcome the vanishing gradient problem, which occurs when training RNNs on long sequences.

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

Q1. What are different evaluation matrix ?
Ans. 
Evaluation matrices are used to assess the performance of models in data science.
• Confusion matrix: used to evaluate the performance of classification models.

• Precision, recall, and F1 score: measures for binary classification models.

• Mean squared error (MSE): evaluates the performance of regression models.

• R-squared: assesses the goodness of fit for regression models.

• Area under the ROC curve (AUC-ROC): evaluates the perfo...read more
Answered by AI
Add your answer